market research method of forecasting suitable

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

How to Choose the Right Forecasting Technique

• John C. Chambers,
• Satinder K. Mullick,
• Donald D. Smith

What every manager ought to know about the different kinds of forecasting and the times when they should be used.

To handle the increasing variety and complexity of managerial forecasting problems , many forecasting techniques have been developed in recent years. Each has its special use, and care must be taken to select the correct technique for a particular application. The manager as well as the forecaster has a role to play in technique selection; and the better they understand the range of forecasting possibilities, the more likely it is that a company’s forecasting efforts will bear fruit.

• JC John C. Chambers is director of operations research at Corning Glass Works. He has previously been affiliated with the Ford Motor Company, North American Aviation, and Ernst and Ernst. His interests center on strategic planning for new products and development of improved forecasting methods.
• SM Satinder K. Mullick is project manager in the Operations Research Department at CGW. He has previously been affiliated with Larsen and Toubro Ltd., India; Bohner and Koehle Maschinenfabrik, West Germany; and Johns Hopkins University. He specializes in strategic and tactical planning for new products.
• DS Donald D. Smith was a senior project leader in the Operations Research Department at CGW, with specific interests in the area of time series analysis and econometrics.

Partner Center

Marketing forecasting — definition, components, and best methods

Marketing uses a significant portion of company budgets. According to a Gartner report , it represents an average of 9.5% of company spending. So before you invest all that money, you need to know which campaigns are most likely to be successful.

Marketing forecasting helps predict which campaigns will yield the highest ROI. This post will guide you through the basics.

What is a marketing forecast?

Benefits of marketing forecasting, components of a marketing forecast.

• Methods for marketing forecasting

A marketing forecast is a comprehensive data analysis to predict the potential success of specific marketing efforts. The purpose is to ensure that a company focuses on the proper marketing and advertising activities across channels and spends its time and money wisely.

Stakeholders and executives need to know that marketing resources are well-spent. That's why, according to The CMO Survey , 8.9% of the average marketing budget is spent on marketing analytics — and will likely keep growing. Marketing forecasting, as an analytical tool, has several advantages.

• Better planning. Marketing projections demonstrate where you’ll probably have more success or failure. Predictions of poor performance can inspire innovation and guide you toward better strategies.
• Easier decision-making. When managers have data, there’s less room for debate about which marketing strategies will work best. Decisions are made on facts rather than hunches, so teams can work confidently.
• Better budgeting and scheduling. It’s easier to allocate resources to specific tactics or channels once you’ve made researched-based calculations.
• Healthier risk management. While marketing forecasts are only a strategic estimate, they can help avoid catastrophes — or help take corrective action when necessary. When you’ve done your homework, there are fewer surprises.

https://main--bacom-blog--adobecom.hlx.page/blog/fragments/definitive-guide-to-marketing-metrics-analytics

There are three considerations that make a marketing forecast effective — the data, the market size under consideration, and your target audience.

1. Accurate data

Accurate forecasts matter. Overestimating success leads to wasted time and effort and a warehouse full of overstock. Underestimating leaves you unprepared to meet demand. To get a helpful outlook on your marketing campaigns, start with accurate data.

First, know your marketing goals and the time and money you can devote to them. If you can only afford a six-month email campaign, then center your marketing projections around that. Keep your options open but be sure to measure what you can realistically achieve.

Next, gather any general statistics and reports you already have available. Consider:

• Third-party data like Google Trends, government statistics, and industry trends and reports
• Company data like past sales reports, competitive intelligence, and customer feedback If your ecommerce site is equipped with good analytics software, you should be able to gather valuable customer insights to help in your forecasting.

2. Market size

Market size is the number of customers to whom you can potentially sell your product. The total addressable market (TAM) is the total potential revenue for a specific product. To get the TAM, multiply the total number of potential customers by your price.

The key is identifying your real customers and what they’re genuinely willing to spend. Don’t take a top-down approach — looking at the total market size and assuming you can easily capture a small percentage. Instead, take a bottom-up approach by showing how your product can reach a specific audience.

Marketing forecasts also help reveal market potential , which is your room for growth. Larger economic trends can drive people to buy — or not. For example, rising gas prices might make it more likely for people to buy your new mopeds. Before committing to a new opportunity, consider natural volatility and sales cycles so you don’t lean too far into a momentary trend.

3. Target audience

Position your product within your market by segmenting the target audience. Building buyer personas is the best way to do this.

A buyer persona is a general sketch of a specific type of customer. It allows you to synthesize audience data and put a face to it. You also can craft a view of your ideal customer. Drafting fictional buyers for different demographics and verticals is an art form, but once you dial it in, you’ll dramatically improve your marketing projections.

Remember that buyer personas should not be static. They are dynamic profiles you hone in over time. Your target audience is apt to change, so factor in what would make them buy at various times. Look for triggers that prompt customers to act.

Marketing forecast data sources

In addition to the hard data you source from your customer data platform (CDP) or other relationship management software, you can collect key insights to inform your marketing forecast from the people with the most experience with your products.

Executive opinion

Asking leadership what they think about a product’s viability and the possible success of specific strategies is a simple place to start. Chief officers often have the most at stake and are intimately acquainted with past performance and challenges. Executives regularly meet with regional marketing managers and share perspectives on what’s working and what strategies they think might create the greatest impact.

Customer or channel surveys

Create customer surveys to test how the market will react to specific products or messaging. Marketers can survey a particular distribution channel, like customers at a retail or online store, or they might target a particular market segment, like middle-aged American males.

Use those surveys to inform your marketing forecast. But remember, while these surveys accurately depict market interest , they don’t necessarily predict sales .

Sales force composite

Because sales reps pitch and sell the product daily, they can offer helpful estimates about future growth. A sales force composite is a survey of the entire sales team to project sales or marketing results.

Salespeople can sometimes be overly optimistic but their opinion is valuable — especially for short-term forecasts. A sales force composite can show how a product or a marketing strategy will succeed in different regions.

Expert opinions

Expert third-party opinions can provide helpful insights as well. But simply soliciting the opinion of a group of experts doesn’t necessarily lead to accurate or helpful conclusions. It’s best to use this method in tandem with quantitative research.

Methods for marketing forecasts

There are several techniques marketers can use to make projections, including qualitative surveys, historical research and projection, and cause-and-effect analysis. The best approach is to use as many methods as possible and then weigh the results against each other.

Delphi technique

The Delphi technique questions anonymous expert panelists over a series of rounds and averages the final round results. It’s more controllable and more accurate than a traditional expert group interview.

Correlation technique

Studying the correlation between different variables is a more sophisticated marketing forecast method. At its simplest, it traces a market factor against marketing performance, usually with a scatter plot graph. You can draw a correlation where trends move in the same direction.

For example, you might study whether CTA clicks go up over time in relation to an email campaign or how many views your product video gets with the support of a Facebook ad.

The correlation technique gets challenging when you factor in multiple trends simultaneously. And remember that correlation does not equal causation — trends can be helpful, but consider other factors and techniques as well.

Time series technique

The time series forecasting method uses various techniques to look at historical patterns in marketing and apply them to upcoming periods. For example, if the company saw a steady 4% increase in website traffic in the past year, marketing can expect the trend to continue. If you notice rates decelerating or accelerating steadily over time, you can factor that in too.

The challenge is that markets are not always stable. Seasonal and cyclical trends affect numbers, but so do unpredictable fluctuations. Use adjustments to account for volatility. For example, a moving average works with the rate of change for several past periods. Exponential smoothing is a moving average that weighs the last period more heavily.

Response model technique

Response models take advantage of direct customer input. Noting customers’ responses to past marketing campaigns can help predict how they’ll react to future efforts. For example, it can gauge what customers are willing to pay for a product.

You can segment customers into categories — demographics, social networks, or how long they’ve been a customer — and then split test or test multiple strategies on different segments at once.

For example, you might split a target audience into three groups and offer a discount to one segment, a buy-one-get-one-free offer to the second, and nothing to the third. Analyzing the results will help you see which offer makes the most sense for your audience in general.

Remember to keep the variables simple. The more options you add, the more complicated and less accurate your analysis becomes.

Access all your marketing forecasting data in one place

Marketing forecasting can better predict which campaigns meet your audience’s needs and your company’s financial goals to yield the most significant ROI.

Once you’ve identified which metrics and data meet your needs, you will need a platform to collect and analyze them. With all your customer data in one easy-to-use platform, you can use any marketing forecasting method to predict which campaigns will be the most efficient.

Adobe Campaign connects big databases and your broader marketing ecosystem, including point-of-sale systems, ecommerce platforms, and offline programs. It helps you understand your market and who your customers are. You can analyze all that data in one place and make better marketing forecasts that lead to stronger sales.

Watch the demo video to learn more about how Adobe Campaign can help you create accurate marketing forecasts that prove your strategies, win budget, and set your team up for success.

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

16.3 Forecasting

Learning objectives.

• List steps in the forecasting process.
• Identify types of forecasting methods and their advantages and disadvantages.
• Discuss the methods used to improve the accuracy of forecasts.

Creating marketing strategy is not a single event, nor is the implementation of marketing strategy something only the marketing department has to worry about. When the strategy is implemented, the rest of the company must be poised to deal with the consequences. As we have explained, an important component is the sales forecast, which is the estimate of how much the company will actually sell. The rest of the company must then be geared up (or down) to meet that demand. In this section, we explore forecasting in more detail, as there are many choices a marketing executive can make in developing a forecast.

Accuracy is important when it comes to forecasts. If executives overestimate the demand for a product, the company could end up spending money on manufacturing, distribution, and servicing activities it won’t need. The software developer Data Impact recently overestimated the demand for one of its new products. Because the sales of the product didn’t meet projections, Data Impact lacked the cash available to pay its vendors, utility providers, and others. Employees had to be terminated in many areas of the firm to trim costs.

Underestimating demand can be just as devastating. When a company introduces a new product, it launches marketing and sales campaigns to create demand for it. But if the company isn’t ready to deliver the amount of the product the market demands, then other competitors can steal sales the firm might otherwise have captured. Sony’s inability to deliver the e-Reader in sufficient numbers made Amazon’s Kindle more readily accepted in the market; other features then gave the Kindle an advantage that Sony is finding difficult to overcome.

The marketing leader of a firm has to do more than just forecast the company’s sales. The process can be complex, because how much the company can sell will depend on many factors such as how much the product will cost, how competitors will react, and so forth—in fact, much of what you have already read about in preparing a marketing strategy. Each of these factors has to be taken into account in order to determine how much the company is likely to sell. As factors change, the forecast has to change as well. Thus, a sales forecast is actually a composite of a number of estimates and has to be dynamic as those other estimates change.

A common first step is to determine market potential , or total industry-wide sales expected in a particular product category for the time period of interest. (The time period of interest might be the coming year, quarter, month, or some other time period.) Some marketing research companies, such as Nielsen, Gartner, and others, estimate the market potential for various products and then sell that research to companies that produce those products.

Once the marketing executive has an idea of the market potential, the company’s sales potential can be estimated. A firm’s sales potential is the maximum total revenue it hopes to generate from a product or the number of units of it the company can hope to sell. The sales potential for the product is typically represented as a percentage of its market potential and equivalent to the company’s estimated maximum market share for the time period. As you can see in Figure 16.8 “A Marketing Plan Timeline Illustrating Market Potential, Sales, and Costs” , companies sell less than potential because not everyone will make a decision to buy their product: some will put off a decision; others will buy a competitor’s product; still others might make do with a substitute product. In your budget, you’ll want to forecast the revenues earned from the product against the market potential, as well as against the product’s costs.

Forecasting Methods

Forecasts, at their basic level, are simply someone’s guess as to what will happen. Each estimate, though, is the product of a process. Several such processes are available to marketing executives, and the final forecast is likely to be a blend of results from more than one process. These processes are judgment techniques and surveys, time series techniques, spending correlates and other models, and market tests.

Judgment and Survey Techniques

At some level, every forecast is ultimately someone’s judgment. Some techniques, though, rely more on people’s opinions or estimates and are called judgment techniques . Judgment techniques can include customer (or channel member or supplier) surveys, executive or expert opinions, surveys of customers’ (or channel members’) intentions or estimates, and estimates by salespeople.

Customer and Channel Surveys

In some markets, particularly in business-to-business markets, research companies ask customers how much they plan to spend in the coming year on certain products. Have you ever filled out a survey asking if you intend to buy a car or refrigerator in the coming year? Chances are your answers were part of someone’s forecast. Similarly, surveys are done for products sold through distributors. Companies then buy the surveys from the research companies or do their own surveys to use as a starting point for their forecasting. Surveys are better at estimating market potential than sales potential, however, because potential buyers are far more likely to know they will buy something—they just don’t know which brand or model. Surveys can also be relatively costly, particularly when they are commissioned for only one company.

Sales Force Composite

A sales force composite is a forecast based on estimates of sales in a given time period gathered from all of a firm’s salespeople. Salespeople have a pretty good idea about how much can be sold in the coming period of time (especially if they have bonuses riding on those sales). They’ve been calling on their customers and know when buying decisions will be made.

Estimating the sales for new products or new promotions and pricing strategies will be harder for salespeople to estimate until they have had some experience selling those products after they have been introduced, promoted, or repriced. Further, management may not want salespeople to know about new products or promotions until these are announced to the general public, so this method is not useful in situations involving new products or promotions. Another limitation reflects salespeople’s natural optimism. Salespeople tend to be optimistic about what they think they can sell and may overestimate future sales. Conversely, if the company uses these estimates to set quotas, salespeople are likely to reduce their estimates to make it easier to achieve quota.

Salespeople are more accurate in their near-term sales estimates, as their customers are not likely to share plans too far into the future. Consequently, most companies use sales force composites for shorter-range forecasts in order to more accurately predict their production and inventory requirements. Konica-Minolta, an office equipment manufacturer, has recently placed a heavy emphasis on improving the accuracy of its sales force composites because the cost of being wrong is too great. Underestimated forecasts result in some customers having to wait too long for deliveries for products, and they may turn to competitors who can deliver faster. By contrast, overestimated forecasts result in higher inventory costs.

Executive Opinion

Executive opinion is exactly what the name implies: the best-guess estimates of a company’s executives. Each executive submits an estimate of the company’s sales, which are then averaged to form the overall sales forecast. The advantages of executive opinions are that they are low cost and fast and have the effect of making executives committed to achieving them. An executive-opinion-based forecast can be a good starting point. However, there are disadvantages to the method, so it should not be used alone. These disadvantages are similar to those of the sales force composites. If the executives’ forecast becomes a quota upon which their bonuses are estimated, they will have an incentive to underestimate the forecast so they can meet their targets. Organizational factors also come into play. A junior executive, for example, is not likely to forecast low sales for a product that his or her CEO is pushing, even if low sales are likely to occur.

Expert Opinion

Expert opinion is similar to executive opinion except that the expert is usually someone outside the company. Like executive opinion, expert opinion is a tool best used in conjunction with more quantitative methods. As a sole method of forecasting, however, expert opinions are often very inaccurate. Just consider how preseason college football rankings compare with the final standings. The football experts’ predictions are usually not very accurate.

Time Series Techniques

Time series techniques examine sales patterns in the past in order to predict sales in the future. For example, with a trend analysis , the marketing executive identifies the rate at which a company’s sales have grown in the past and uses that rate to estimate future sales. For example, if sales have grown 3 percent per year over the past five years, trend analysis would assume a similar 3 percent growth rate next year.

A simple form of analysis such as this can be useful if a market is stable. The problem is that many markets are not stable. A rapid change in any one of a market’s dynamics is likely to result in wide swings in growth rates. Just think about auto sales before, during, and after the government’s Cash for Clunkers program. What sold the previous month could not account for the effects of the program. Consequently, if an executive were to have estimated auto sales based on the rate of change for the previous period, the estimate would have been way off.

Figure 16.10

The federal government’s Cash for Clunkers program resulted in a significant short-term increase in new car sales and filled junkyards with thousands of clunkers!

ashley.adcox – Field Of Clunkers Pt. II – CC BY-NC-ND 2.0.

The Cash for Clunkers program was an unusual situation; many products may have wide variations in demand for other reasons. Trend analysis can still be useful in these situations but adjustments have to be made to account for the swings in rates of change. Two common adjustments are the moving average , whereby the rate of change for the past few periods is averaged, and exponential smoothing , a type of moving average that puts more emphasis on the most recent period.

Correlates and Other Models

A number of more sophisticated models can be useful in forecasting sales. One fairly common method is a correlational analysis , which is a form of trend analysis that estimates sales based on the trends of other variables. For example, furniture-company executives know that new housing starts (the number of new houses that are begun to be built in a period) predict furniture sales in the near future because new houses tend to get filled up with new furniture. Such a correlate is considered a leading indicator , because it leads, or precedes, sales. The Conference Board publishes an Index of Leading Indicators, which is a single number that represents a composite of commonly used leading indicators. Some of these leading indicators are housing starts, wholesale orders, orders for durable goods (items like refrigerators, air conditioning systems, and other long-lasting consumer products), and even consumer sentiment, or how consumers think the economy is doing.

Response Models

Some companies create sophisticated statistical models called response models , which are based on how customers have responded in the past to marketing strategies. JCPenney, for example, takes previous sales data and combines it with customer data gathered from the retailer’s Web site. The models help JCPenney see how many customers are price sensitive and only buy products when they are on sale and how many customers are likely to respond to certain offers. The retailer can then estimate the sales for products by market segment based on the offers and promotions directed at those segments.

Market Tests

A market test is an experiment in which the company launches a new offering in a limited market in order to gain real-world knowledge of how the market will react to the product. Since there isn’t any historical data on how the product has done, response models and time-series techniques are not effective. A market test provides some measure of sales in response to the marketing plan, so in that regard, it is like a response model, just based on limited data. The demand for the product can then be extrapolated to the full market. However, remember that market tests are visible to your competitors, and they can undertake actions, such as drastic price cuts, to skew your results.

Figure 16.11

HEB uses Waco, Texas, as a test market, combining data from its loyalty program with sales data to see who buys what and at what price.

Wikimedia Commons – CC BY-SA 3.0.

The grocery chain HEB uses Waco, Texas, as a test site. HEB has a loyalty program that enables it to collect lots of data on its customers. When HEB wants to test market a new product, the firm does it in Waco, where individual customer data can be combined with sales data. Testing in Waco tells HEB who is likely to buy the product and at what price, information that makes extrapolating to their larger market more accurate.

Building Better Forecasts

At best, a forecast is a scientific estimate, but really, a forecast is still just a sophisticated guess. Still, there are steps that can enhance the likelihood of success. The first step is to commit to accuracy. At Konica-Minolta, regional vice presidents are rewarded for being accurate and punished for being wrong about their forecasts, no matter what the direction of them is. As we mentioned earlier, underestimating is considered by Konica-Minolta leadership to be just as bad as overestimating sales.

We’ve also mentioned how salespeople and managers will lower estimates if the estimates are used to set quotas. Using forecasts properly is another factor that can improve forecasting accuracy. But there are other ways to make forecasts more accurate. These begin with picking the right methods for your business.

Pick the Right Method(s) for Your Business and Your Decision

Some products have very short selling cycles; others take a long time to produce and sell. What is appropriate for a fast-moving consumer good like toothpaste is not appropriate for a durable good like a refrigerator. A response model might work for Crest toothpaste in the short term, but longer-term forecasts might require a sophisticated time-series technique. By contrast, Whirlpool might find, for example, that channel surveys are better predictors of refrigerator sales over the long term.

Use Multiple Methods

Since forecasts are estimates, the more estimates generated from various methods, the better. For example, combining expert opinions with a trend analysis could help you understand not only what is happening but also why. Every forecast results in decisions, such as the decision to hire more people, add manufacturing capacity, order supplies, and so forth. In addition, practice makes perfect, as they say. The more forecasts you have to make and resulting decisions you have to live with, the better you will get at forecasting.

Use Many Variables

Forecasting for smaller business units first can result in greater accuracy. For example, JCPenney may estimate sales by region first, and then roll that information up into a national sales forecast. By forecasting locally, more variables can be considered, and with more variables comes more information, which should help the accuracy of the company’s overall sales forecast. Similarly, JCPenney may estimate sales by market segment, such as women over age fifty. Again, forecasting in a smaller segment or business unit can then enable the company to compare such forecasts to forecasts by product line and gain greater accuracy overall.

Use Scenario-Based Forecasts

One forecast is not enough. Consider what will happen if conditions change. For example, how might your forecast change if your competitors react strongly to your strategy? How might it change if they don’t react at all? Or if the government changes a policy that makes your product tax free? All of these factors will influence sales, so the smart executive considers multiple scenarios. While the executive may not expect the government to make something tax free, scenarios can be created that consider favorable government regulation, stable regulation, and negative regulation, just as one can consider light competitive reaction, moderate reaction, or strong reaction.

Track Actual Results and Adjust

As time goes on, forecasts that have been made should be adjusted to reflect reality. For example, Katie Scallan-Sarantakes may have to do an annual forecast for Scion sales, but as each month goes by, she has hard sales data with which to adjust future forecasts. Further, she knows how strongly competition has reacted and can adjust her estimates accordingly. So, even though she may have an annual forecast, the forecast changes regularly based on how well the company is doing.

Key Takeaway

A forecast is an educated guess, or estimate, of sales in the future. Accuracy is important because so many other decisions a firm must make depend on the forecasts. When a company forecasts sales, it has to consider market potential and sales potential. Many methods of forecasting exist, including expert opinion, channel and customer surveys, sales force composites, time series data, and test markets.

Better forecasts can be obtained by using multiple methods, forecasting for various scenarios, and tracking actual data (including sales) and adjusting future forecasts accordingly.

Review Questions

• Which forecasting method would be most accurate for forecasting sales of hair-care products in the next year? How would your answer change if you were forecasting for the next month? For home appliances?
• What is the role of expert opinion in all forecasts?
• How can forecasting accuracy be improved?

Principles of Marketing Copyright © 2015 by University of Minnesota is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License , except where otherwise noted.

Share This Book

• Perspectives
• Best Practices
• Inside Amplitude
• Customer Stories
• Contributors

Marketing Forecasting 101: Using Analytics for Future Insights

Use marketing forecasting to predict future performance and optimize your product and marketing strategies accordingly.

Marketing forecasting is how companies make educated predictions about their future performance within their specific target markets . By using market research and historical data, marketers can make forecasts about demands and trends that will help them better predict sales.

The forecasting process helps you understand the effectiveness of your marketing strategies and puts you in a better position to optimize your efforts going forward. By understanding the strengths and weaknesses of your campaigns, you can better predict what will work and what techniques to omit altogether.

• Marketing forecasting is how companies make data-driven predictions about future events within their sector.
• Predicting future trends
• Optimizing marketing activity
• Reducing customer churn
• Acting proactively instead of reactively
• More accurate budgeting
• Better control over your inventory
• Better employee allocation based on your needs
• Techniques such as correlational analysis, predictive analytics, and conducting customer surveys give you the information you need to perfect your forecasting.
• Typical marketing forecasting involves an eight-step process that includes plotting your revenue cycle, analyzing your customer data, and taking action on the insights you’ve uncovered.

What is marketing forecasting?

A marketing forecast helps businesses conduct trend analysis by predicting future market characteristics, sales data, and the growth rate within their sector . Forecasting means you replace guesswork with an empirical, data-focused approach to planning. There are several different types of forecasting techniques that allow businesses to obtain data using both qualitative and quantitative methods.

Businesses use behavioral analytics , market research, historical data, and forecasting methods to make predictions on things like:

• Predicted customer behaviors throughout the user journey
• Number of leads likely generated within a period
• Rate of leads moving through the sales funnel
• Effectiveness of different marketing campaigns and channels in acquiring new customers
• Market potential of the product : how much potential revenue your product or service will likely generate within a specific market.
• Future sales numbers and revenue impact
• Impact on critical product metrics around acquisition, retention, and monetization

A marketing forecast takes all of these predictions and consolidates them into one analysis, allowing your business to get a complete picture of the future. These insights enable you to carry out more strategic planning, knowing you have all the necessary information.

Main benefits of marketing forecasting

Your marketing forecast is foundational to your marketing plan and product forecast. It helps you understand how your marketing and product roadmaps will perform, so you can strategically plan your future and guide your team’s decision-making.

Several benefits come from taking this approach:

Insight into future trends

Trend forecasting involves using market and consumer data to predict how customer behaviors and purchasing habits will likely shift over time. Predicting future trends in the market helps you outpace your competitors during times of change.

There are several different types of trend forecasting patterns that you can analyze, such as constant and linear patterns in data. For example, you can predict when demand for certain products will likely rise or fall and prepare accordingly. Trend forecasting also provides you insights to predict shifting customer behaviors and expectations. You can use this knowledge to adjust your marketing or product strategy .

More targeted marketing activity

You can use predictive customer analytics to understand user behavior and forecast which behaviors will likely have higher conversion rates. These insights will help you craft more effective messaging, refine your pricing and packaging, and increase your cross-sell and upsells.

A predictive analytics tool like Amplitude Audiences leverages algorithms that make connections between specific behaviors and conversion. For example, you might find that people who arrive on your landing page from social media ads are more likely to sign up for a free trial. You might invest more heavily in your social media marketing efforts with this insight.

Forecasting helps you understand which marketing channels will be most effective based on trends, market data, and user behavior .

Increase customer retention

Another benefit of utilizing predictive analytics is the ability to target customers who are at risk of churning through churn rate cohort analysis . Once you’ve identified these at-risk customers, you can experiment with the most effective marketing campaigns to increase retention and boost loyalty. For example, you might employ inverse pricing—offering customers with a high likelihood of churning a larger discount or incentive.

In this inverse pricing example, a streaming company might offer customers with a low likelihood of upgrading a larger incentive than those with a high likelihood of upgrading.

Proactive vs. reactive planning

Predicting and planning for several possible scenarios helps you be more proactive in your approach. Implementing contingency plans allows you to build more resilience to otherwise unexpected events. These could be external or internal events such as shifts in economic trends, changes in customer sentiments, technological advancements, or losing customers to competitors.

Precise budgeting

You can better allocate funds to different areas of your business through budget forecasting. Look at your sales forecasts and check them against your expense forecasts for both the short and long term. This way, you can budget smarter for different costs like:

• MarTech tools
• Paid advertising
• Marketing campaigns
• Product launch events
• Engineering and product costs

Deciding to invest in things like developing new products, hiring more employees, or boosting digital marketing efforts can be risky. But understanding what your company’s financial situation will look like further down the line helps remove a lot of the uncertainty.

Better inventory management

For ecommerce businesses, inventory forecasting ensures you have the right supply to meet customer demand across your digital channels. Ecommerce inventory management involves tracking the location, amount, pricing, and mix of available inventory. By basing your orders on an accurate forecast, you don’t have to worry about over or under-ordering products for your online store.

Read the Ultimate Guide to Analytics for Ecommerce to learn how to further optimize your online business.

More accurate employee allocation

HR forecasting ensures you have the right number of employees to meet business and customer needs, leading to a better customer experience .

For example, if you have an ecommerce business, you might forecast a spike in sales during the holidays and need extra customer service representatives to respond to inquiries. Or perhaps you plan on hosting a marketing event for your B2B SaaS tool’s new product launch and forecast an increase in inbound sales requests from prospects and customers.

Common marketing forecasting techniques

Predicting what will happen in the future might sound tricky, but you can use several techniques to obtain accurate forecasts. Each one will give you different insights and metrics, but a mixture gives you a more comprehensive picture of what you’re trying to predict.

Analyzing correlations

Correlational analysis helps you understand the relationships between your customers and your product. Through your analysis, you might find that certain features you implement in your platform have positive or negative effects on your customer experience.

This information provides product managers with the knowledge of what aspects of their product line contribute to (or hinder) customer retention or engagement, which helps them optimize their products for growth.

You can also analyze correlations related to your marketing efforts. You might find that customer cohorts acquired through referral programs tend to have a higher customer lifetime value (CLV) than those from social media campaigns and optimize accordingly.

Predictive analytics

With Audiences’ Predictions , you can build cohorts based on specific attributes or behaviors that will help you identify product and marketing tweaks to improve conversion. Predictive analytics can help you:

• Personalize your marketing messaging
• Choose the right pricing for your target audience
• Cross-sell and upsell based on historical data to increase CLV
• Use inverse pricing techniques to develop the most effective actions for different audiences based on how likely they are to perform the desired actions.

Seeking executive and expert opinions

These are simple knowledge-based opinions you can obtain from well-informed executives in your company and external experts in your industry. While they may not have hard numbers to “prove” their opinions, their extensive experience lends much weight to their views and can be helpful in forecasting.

For this approach to be accurate, opinions must be collected and analyzed using tried and tested qualitative methods. One example could be thematic analysis, where you extract common themes from raw qualitative data, such as interview transcripts.

Conducting customer surveys

Customer surveys involve carrying out research with potential customers about new products or finding out how your current customers feel about your existing products. You can collect information directly from your current and potential customers to help you:

• Understand customer intent
• Collect demographic data about your target customers
• Get an idea of their preferred price range

Once you have the raw data, you can analyze it to get a feel for your customers’ sentiments. You should then use those sentiments in your marketing forecast. If 90% of your customers say they love your new product, sales will likely be high.

Gathering information from your sales team

Your sales team is at the front of your marketing activities. They have insight from their daily experiences into how your products perform, the effectiveness of your marketing activities, and your customer sentiment. You can collect this information by conducting interviews and surveys or hosting focus groups.

One limitation is that your sales team can only provide information about your existing products and current marketing efforts. However, you can use the information they give you and insights from your sales funnel to understand how other marketing efforts will work. For example, if customers respond well to a specific ad for a soon-to-be-updated product, you know you should use a similar ad when you roll out the new version. Yes, the new product and ad don’t exist yet, but your salespeople can still offer valuable insights.

Implementing time series techniques

Time series techniques look at sales patterns over various periods. You can use them to uncover patterns over the past month, quarter, or year that will predict future sales. For example, if there was a 3% growth in sales every year for the past three years, it’s safe to assume that the next year will see similar growth.

It’s helpful to know what will happen in a specific period to make more strategic product and marketing decisions that will help you acquire a larger market share. For example, you can predict how many items you’ll sell through your ecommerce channels or how many customers will upgrade to the premium version of your digital product.

How to conduct a marketing forecast

Even though there are several different forecasting tools that companies can use to carry out their analysis, there is a basic methodology to be followed:

• Plot out the stages of your revenue cycle. Track a customer’s typical journey from start to purchase using customer journey analytics . This gives you foundational knowledge about your customer journey.
• Identify the leads that you would like to track. Pick a few high-value customer cohorts whose journey you want to optimize. These are market segments you identified as most valuable to you during your market research.
• Obtain information on how every customer experiences their lifecycle. If you’re an ecommerce company, use metrics like conversion rate and cart abandonment rate to understand the percentage of online store visitors who make a purchase and those who place items in their cart but never complete their purchase.
• Determine the number of leads who will move through your sales funnel in a given period. If you’re a B2B SaaS company, knowing the number of leads will give you a rough idea of how many new customers you can expect, which offers you a great start to your forecast. You can determine the number of leads by looking at your recent sales funnel trends and talking to your sales team.
• Model the flow of new and current leads through each customer journey stage. Once you’ve gathered all the information from the previous steps, you can plot out the typical journey of a customer lifecycle. This helps you make better predictions based on tried and tested customer experiences.
• Make predictions based on behavioral customer data . Using insights from past customer behavior, a tool like Audiences can predict future behaviors using AI and machine learning technology.
• Analyze your results and finalize your marketing forecast. With this information, you’re in a stronger position to predict future sales, trends, and general consumer behavior.
• Take action on your insights. Forecasting what will happen in the future is only helpful if you take action. Use your predictions to test new marketing campaigns, product personalizations, pricing strategies, and more.

Learn how you can leverage the power of predictive analytics with a personalized Audiences consultation . Or see how customers are behaving in your digital product today with a free Amplitude account .

• What is Ecommerce Inventory Management? , Big Commerce
• What Is Trend Forecasting? , Chron
• Customer Acquisition vs. Retention , Invesp

About the Author

More best practices.

Discover the insights of 300+ marketing professionals on the essential tools, resources, and skills for success.

• · Brandwatch Academy
• Forrester Wave

Brandwatch Consumer Research

Formerly the Falcon suite

Formerly Paladin

Published October 17 th 2023

10 Essential Methods for Effective Consumer and Market Research

When it comes to understanding the world around you, market research is an essential step.

We live in a world that’s overflowing with information. Sifting through all the noise to extract the most relevant insights on a certain market or audience can be tough.

That’s where market research comes in – it’s a way for brands and researchers to collect information from target markets and audiences.

Once reliant on traditional methods like focus groups or surveys, market research is now at a crossroads. Newer tools for extracting insights, like social listening tools, have joined the array of market research techniques available.

Here, we break down what market research is and the different methods you can choose from to make the most of it.

What is market research, and why is it critical for you as a marketer?

Market research involves collecting and analyzing data about a specific industry, market, or audience to inform strategic decision-making. It offers marketers valuable insights into the industry, market trends, consumer preferences, competition, and opportunities, enabling businesses to refine their strategies effectively.

By conducting market research, organizations can identify unmet needs, assess product demands, enhance value propositions, and create marketing campaigns that resonate with their target audience. 

This practice serves as a compass, guiding businesses in making data-driven decisions for successful product launches, improved customer relationships, and a stronger positioning in the business landscape. 

For marketers and insights professionals, market research is an indispensable tool. It helps them make smarter decisions and achieve growth and success in the market.

These 10 market research methods form the backbone of effective market research strategies. 

Continue reading or jump directly to each method by tapping the link below.

• Focus groups
• Consumer research with social media listening
• Experiments and field trials
• Observation
• Competitive analysis
• Public domain data
• Buy research
• Analyze sales data

Use of primary vs secondary market research

Market research can be split into two distinct sections: primary and secondary. These are the two main types of market research.

They can also be known as field and desk, respectively (although this terminology feels out of date, as plenty of primary research can be carried out from your desk).

Primary (field) research

Primary market research is research you carry out yourself. Examples of primary market research methods include running your own focus groups or conducting surveys. These are some of the key methods of consumer research. The ‘field’ part refers to going out into the field to get data.

Secondary (desk) research

Secondary market research is research carried out by other people that you want to use. Examples of secondary market research methods include studies carried out by researchers or financial data released by companies.

10 effective methods to do market research

The methods in this list cover both areas. Which ones you want to use will depend on your goals. Have a browse through and see what fits.

1. Focus groups

It’s a simple concept but one that can be hard to put into practice.

You bring together a group of individuals into a room, record their discussions, and ask them questions about various topics you are researching. For some, it’ll be new product ideas. For others, it might be views on a political candidate.

From these discussions, the organizer will try to pull out some insights or use them to judge the wider society’s view on something. The participants will generally be chosen based on certain criteria, such as demographics, interests, or occupations.

A focus group’s strength is in the natural conversation and discussion that can take place between participants (if they’re done right).

Compared to a questionnaire or survey with a rigid set of questions, a focus group can go off on tangents the organizer could not have predicted (and therefore not planned questions for). This can be good in that unexpected topics can arise; or bad if the aims of the research are to answer a very particular set of questions.

The nature of the discussion is important to recognize as a potential factor that skews the resulting data. Focus groups can encourage participants to talk about things they might not have otherwise, and others might impact the group. This can also affect unstructured one-on-one interviews.

In survey research, survey questions are given to respondents (in person, over the phone, by email, or via an online form). Questions can be close-ended or open-ended. As far as close-ended questions go, there are many different types:

• Dichotomous (two choices, such as ‘yes’ or ‘no’)
• Multiple choice
• Rating scale
• Likert scale (common version is five options between ‘strongly agree’ and ‘strongly disagree’)
• Matrix (options presented on a grid)
• Demographic (asking for information such as gender, age, or occupation)

Surveys are massively versatile because of the range of question formats. Knowing how to mix and match them to get what you need takes consideration and thought. Different questions need the right setup.

It’s also about how you ask. Good questions lead to good analysis. Writing clear, concise questions that abstain from vague expressions and don’t lead respondents down a certain path can help your results reflect the true colors of respondents.

There are a ton of different ways to conduct surveys as well, from creating your own from scratch or using tools that do lots of the heavy lifting for you.

3. Consumer research with social media listening

Social media has reached a point where it is seamlessly integrated into our lives. And because it is a digital extension of ourselves, people freely express their opinions, thoughts, and hot takes on social media.

Because people share so much content on social media and the sharing is so instant, social media is a treasure trove for market research. There is plenty of data to monitor , tap into, and dissect.

By using a social listening tool, like Consumer Research , researchers can identify topics of interest and then analyze relevant social posts. For example, they can track brand mentions and what consumers are saying about the products owned by that brand. These are real-world consumer research examples.

View this post on Instagram A post shared by Brandwatch (@brandwatch)

Social media listening democratizes insights, and is especially useful for market research because of the vast amount of unfiltered information available. Because it’s unprompted, you can be fairly sure that what’s shared is an accurate account of what the person really cares about and thinks (as opposed to them being given a subject to dwell on in the presence of a researcher).

You might like

Your complete social listening guide.

Learn how to get started with social listening

4. Interviews

In interviews, the interviewer speaks directly with the respondent. This type of market research method is more personal, allowing for communication and clarification, making it good for open-ended questions. Furthermore, interviews enable the interviewer to go beyond surface-level responses and investigate deeper.

However, the drawback is that interviews can be time-intensive and costly. Those who opt for this method will need to figure out how to allocate their resources effectively. You also need to be careful with leading or poor questions that lead to useless results. Here’s a good introduction to leading questions .

5. Experiments and field trials

Field experiments are conducted in the participants’ environment. They rely on the independent variable and the dependent variable – the researcher controls the independent variable in order to test its impact on the dependent variable. The key here is to establish whether there’s causality.

For example, take Hofling’s experiment that tested obedience, conducted in a hospital setting. The point was to test if nurses followed authority figures (doctors) and if the authority figures’ rules violated standards (The dependent variable being the nurses, the independent variable being a fake doctor calling up and ordering the nurses to administer treatment.)

According to Simply Psychology , there are key strengths and limitations to this method.

The assessment reads:

• Strength: Behavior in a field experiment is more likely to reflect real life because of its natural setting, i.e., higher ecological validity than a lab experiment.
• Strength: There is less likelihood of demand characteristics affecting the results, as participants may not know they are being studied. This occurs when the study is covert.
• Limitation: There is less control over extraneous variables that might bias the results. This makes it difficult for another researcher to replicate the study in exactly the same way.

There are also massive ethical implications for these kinds of experiments and experiments in general (especially if people are unaware of their involvement). Don’t take this lightly, and be sure to read up on all the guidelines that apply to the region where you’re based.

6. Observation

Observational market research is a qualitative research method where the researcher observes their subjects in a natural or controlled environment. This method is much like being a fly on the wall, but the fly takes notes and analyzes them later. In observational market research, subjects are likely to behave naturally, which reveals their true selves. 

They are not under much pressure. However, if they’re aware of the observation, they can act differently.

This type of research applies well to retail, where the researcher can observe shoppers’ behavior by day of the week, by season, when discounts are offered, and more. However, observational research can be time-consuming, and researchers have no control over the environments they research.

7. Competitive analysis

Competitive analysis is a highly strategic and specific form of market research in which the researchers analyze their company’s competitors. It is critical to see how your brand stacks up to rivals. 

Competitive analysis starts by defining the product, service, brand, and market segment. There are different topics to compare your firm with your competitors. It could be from a marketing perspective: content produced, SEO structure, PR coverage, and social media presence and engagement. It can also be from a product perspective: types of offerings, pricing structure. SWOT analysis is key in assessing strengths, weaknesses, opportunities, and threats.

We’ve written a whole blog post on this tactic, which you can read here .

8. Public domain data

The internet is a wondrous place. Public data exists for those strapped for resources or simply seeking to support their research with more data.  With more and more data produced every year, the question about access and curation becomes increasingly prominent – that’s why researchers and librarians are keen on open data.

Plenty of different types of open data are useful for market research: government databases, polling data, “fact tanks” like Pew Research Center, and more. 

Furthermore, APIs grant developers programmatic access to applications. A lot of this data is free, which is a real bonus.

9. Buy research

Money can’t buy everything, but it can buy research. Subscriptions exist for those who want to buy relevant industry and research reports. Sites like Euromonitor, Statista, Mintel, and BCC Research host a litany of reports for purchase, oftentimes with the option of a single-user license or a subscription.

This can be a massive time saver, and you’ll have a better idea of what you’re getting from the very beginning. You’ll also get all your data in a format that makes sense, saving you effort in cleaning and organizing.

10. Analyze sales data

Sales data is like a puzzle piece that can help reveal the full picture of market research insights. Essentially, it indicates the results. Paired with other market research data, sales data helps researchers better understand actions and consequences. Understanding your customers, their buying habits, and how they change over time is important.

This research will be limited to customers, and it’s important to keep that in mind. Nevertheless, the value of this data should not be underestimated. If you’re not already tracking customer data, there’s no time like the present.

Choosing the right market research method for your strategy

Not all methods will be right for your situation or your business. Once you’ve looked through the list and seen some that take your fancy, spend more time researching each option.You’ll want to consider what you want to achieve, what data you’ll need, the pros and cons of each method, the costs of conducting the research, and the cost of analyzing the results.

Get it right, and it’ll be worth all the effort.

Former Brandwatch Employee

Share this post

Brandwatch bulletin.

Offering up analysis and data on everything from the events of the day to the latest consumer trends. Subscribe to keep your finger on the world’s pulse.

New: Consumer Research

Make the world your focus group.

With Brandwatch Consumer Research, you can turn billions of voices into valuable insights.

More in marketing

How to market your sustainability as a brand in 2024.

By Emily Smith Mar 18

The Swift Effect: What Brands Can Learn from Taylor Swift

By Emily Smith Feb 29

How B2B Brands Can Benefit from Social Listening

By Ksenia Newton Feb 23

7-Step Guide: Choosing the Right Social Media Monitoring Tool for You

By Emily Smith Feb 20

We value your privacy

We use cookies to improve your experience and give you personalized content. Do you agree to our cookie policy?

By using our site you agree to our use of cookies — I Agree

Falcon.io is now part of Brandwatch. You're in the right place!

Existing customer? Log in to access your existing Falcon products and data via the login menu on the top right of the page. New customer? You'll find the former Falcon products under 'Social Media Management' if you go to 'Our Suite' in the navigation.

Paladin is now Influence. You're in the right place!

Brandwatch acquired Paladin in March 2022. It's now called Influence, which is part of Brandwatch's Social Media Management solution. Want to access your Paladin account? Use the login menu at the top right corner.

• Entrepreneurs
• News About Crunchbase
• New Features
• Partnerships

The Types of Market Research [+10 Market Research Methods]

• Market research

Jaclyn Robinson, Senior Manager of Content Marketing at Crunchbase

Market research can help startups understand where they should be placing their resources and time. It can tell you everything from how people are perceiving your company, as well as which features to drop or continue developing. And while there are plenty of ways to conduct market research, not every market research method is right for every situation.

Search less. Close more.

Grow your revenue with all-in-one prospecting solutions powered by the leader in private-company data.

Market research can help play a major role in developing your product, marketing, and overall business strategy. Understanding the different market research methods can be the difference between wasting months of engineering time or exceeding your ambitious revenue targets.

We review the types of market research as well as the market research methods you can pursue based on your primary objectives and business goals.

The 2 types of market research

All market research falls under two distinct categories: primary research and secondary research.

Primary research looks at any data you collect yourself (or someone you pay). It encompasses analyzing current sales, metrics, and customers. It also takes into account the effectiveness of current practices, while taking competitors into account.

Secondary research looks at data that has already been published by others. It includes reports and studies from other companies, government organizations, and others in your industry.

10 market research methods

The type of data you need will decide which market research technique to use. Here are the most commonly used market research methods:

Primary research methods

These primary research methods will help you identify both qualitative and quantitative data. Qualitative data is information that cannot be measured while qualitative data is taken from a large sample size and is a statistically significant mathematical analysis.

1. Interviews

Great for: expert advice

Consisting of one-on-one discussions, interviews are a great source of qualitative data. You can either perform interviews by telephone, video conference, or face-to-face. Interviews are great for an in-depth look for target audience insights.

In-depth interviews are great when expert advice is needed or when discussing highly complex or sensitive topics. Interviews are usually 10 to 30 minutes long with 25 to 75 respondents.

Great for: understanding brand awareness, satisfaction and loyalty analysis, pricing research, and market segmentation .

One of the most commonly used market research methods, Surveys are an easy way to understand your target audience and allow you to test a large sample size to determine if findings are true across a larger segment of your customers.

3. Questionnaires

Great for: Customer feedback and satisfaction surveys (NPS surveys), and when you want more detail on your target audience and customer base.

Do not confuse questionnaires for surveys !  While surveys are aggregated for statistical analysis, questionnaires are a set of written questions used for collecting information.

Questionnaires are used to collect information rather than draw a conclusion.  Surveys can include a questionnaire, but a survey must aggregate and analyze the responses to the questions.

When writing questionnaires for market research, keep the number of questions in mind.

In one study, SurveyMonkey found that questionnaires with 40 questions have about a 10% lower response rate than questionnaires with 10 questions . The more questions, the less likely people will finish your questionnaire.

4. Focus groups

Great for: Price testing, advertising concepts, product/messaging testing

Even with the rise of big data, focus groups have remained an integral part of how companies build their products, strategy, and messaging. Focus groups are intentionally compromised by a group of purposefully selected individuals. Above all, the collaborative setting ensures that members of the group are able to interact and influence each other.

Typically these open and interactive groups are composed of around five to 12 screened individuals . Make sure that your participants are diverse so you can get a range of opinions and you have enough representation from several segments of your market.

Many smaller startups will conduct DIY focus groups and will use video conferencing technology, which is one of the most cost-effective and time-efficient market research methods.

This is a great resource to see some good questions to ask your focus groups as well as what topics focus groups should touch on.

5. User groups

Great for: Feature testing, UX and web design feedback

User groups are used to gather UX data and provide insight for website design. User groups usually meet regularly to discuss their experience with a product, while researchers capture their comments.

Here’s a great guide on how to format questions for user groups .

6. Test markets

Great for: Testing new marketing campaigns

Test markets represent a larger market. Using a test group as well as a control group can show you the success of a new landing page, messaging copy, or CTA button. We particularly like the free version of Google Optimize to get quantitative data on how your experiment is performing based on a specific goal.

Secondary research methods

Secondary research can help establish a starting point prior to diving into more expensive primary research techniques. While there is a lot of data on the web regarding basic statistics, you may have to purchase a distinct data provider for a more in-depth look at your market.

Crunchbase Pro and Marketplace partners are a great and inexpensive way to start your secondary research directly on Crunchbase.com.

7. Competitor benchmarks

Great for: Understanding your revenue, churn, operating costs, sales, profit margin, and burn rate.

Competitor benchmarks are the most valuable and widely used of the secondary research methods. Moreover, competitor benchmarks measure specific growth metrics or key performance indicators in comparison to business within the same industry and of a similar size.

You can use Crunchbase Pro to find how much companies in a certain industry are raising and who are the leading players with our global coverage on companies ranging from pre-seed to late-stage. So, as one of the most informative of the market research methods, competitive benchmarks are a great way to inform your business strategy. 

Free Crunchbase registered users have access to revenue estimates as well as web traffic data.

8. Sales data

Great for: Understanding your audience and where to place marketing efforts.

Taking a look at internal sales data not only reveals profitability but also helps market researchers segment customer trends.

However, taking a look at competitive sales data is a great way to make sure that you’re meeting the numbers you should be targeting as well as capturing the full potential of the market

9. Government publications and statistics

Great for: General demographic information and larger trends

The U.S. Census Bureau is a great resource of national demographic data. You can also review patents as a preview of industry trends and future innovation.

Also, you can find additional data and research from Data.gov , The World Bank , as well as the Pew Research Center to help inform your market research decisions.

10. Commercial data

Great for: Greater insight into industry trends and reports

If you’re interested in purchasing secondary market research, commercial data is available. For comprehensive reports, Mintel and IBISWorld are both traditional market research companies that provide commercial data.

Additionally, to choose which type of market research method is best for your goal, follow this graph from Relevant Insights. Begin with the metric you’re trying to move and then backtrack into a targeted market research method.

How can Crunchbase help with my market research?

Crunchbase gives market researchers flexible access to Crunchbase’s complete company data. Innovative teams and leaders in market research rely on Crunchbase’s live company data to build powerful internal databases and research insights in respective industries. Learn more about how Crunchbase can help you with your market research .

• Originally published March 14, 2019, updated April 26, 2023

You may also like

• 10 min read

How to Do Market Research for a Startup: Tips for Success

Eastern Europe Industry Review: Russia-Connected SPACs, New VC Darlings, Food Delivery Disruption

By Adrien Henni, Chief Editor, East-West Digital News

Women In Russian VC: How Gender Stereotypes Hinder Investment

Daria Zharkova, Senior Research Manager at Dsight

The all-in-one prospecting solution

• Find the right companies
• Identify the right contacts
• Connect with decision-makers

• Business Essentials
• Leadership & Management
• Credential of Leadership, Impact, and Management in Business (CLIMB)
• Entrepreneurship & Innovation
• *New* Digital Transformation
• Finance & Accounting
• Business in Society
• For Organizations
• Support Portal
• Media Coverage
• Founding Donors
• Leadership Team

• Harvard Business School →
• HBS Online →
• Business Insights →

Business Insights

Harvard Business School Online's Business Insights Blog provides the career insights you need to achieve your goals and gain confidence in your business skills.

• Career Development
• Communication
• Decision-Making
• Earning Your MBA
• Negotiation
• News & Events
• Productivity
• Staff Spotlight
• Student Profiles
• Work-Life Balance
• Alternative Investments
• Business Analytics
• Business Strategy
• Business and Climate Change
• Design Thinking and Innovation
• Digital Marketing Strategy
• Disruptive Strategy
• Economics for Managers
• Entrepreneurship Essentials
• Financial Accounting
• Global Business
• Launching Tech Ventures
• Leadership Principles
• Leadership, Ethics, and Corporate Accountability
• Leading with Finance
• Management Essentials
• Negotiation Mastery
• Organizational Leadership
• Power and Influence for Positive Impact
• Strategy Execution
• Sustainable Business Strategy
• Sustainable Investing
• Winning with Digital Platforms

7 Financial Forecasting Methods to Predict Business Performance

• 21 Jun 2022

Much of accounting involves evaluating past performance. Financial results demonstrate business success to both shareholders and the public. Planning and preparing for the future, however, is just as important.

Shareholders must be reassured that a business has been, and will continue to be, successful. This requires financial forecasting.

Here's an overview of how to use pro forma statements to conduct financial forecasting, along with seven methods you can leverage to predict a business's future performance.

What Is Financial Forecasting?

Financial forecasting is predicting a company’s financial future by examining historical performance data, such as revenue, cash flow, expenses, or sales. This involves guesswork and assumptions, as many unforeseen factors can influence business performance.

Financial forecasting is important because it informs business decision-making regarding hiring, budgeting, predicting revenue, and strategic planning . It also helps you maintain a forward-focused mindset.

Each financial forecast plays a major role in determining how much attention is given to individual expense items. For example, if you forecast high-level trends for general planning purposes, you can rely more on broad assumptions than specific details. However, if your forecast is concerned with a business’s future, such as a pending merger or acquisition, it's important to be thorough and detailed.

Access your free e-book today.

Forecasting with Pro Forma Statements

A common type of forecasting in financial accounting involves using pro forma statements . Pro forma statements focus on a business's future reports, which are highly dependent on assumptions made during preparation⁠, such as expected market conditions.

Because the term "pro forma" refers to projections or forecasts, pro forma statements apply to any financial document, including:

• Income statements
• Balance sheets
• Cash flow statements

These statements serve both internal and external purposes. Internally, you can use them for strategic planning. Identifying future revenues and expenses can greatly impact business decisions related to hiring and budgeting. Pro forma statements can also inform endeavors by creating multiple statements and interchanging variables to conduct side-by-side comparisons of potential outcomes.

Externally, pro forma statements can demonstrate the risk of investing in a business. While this is an effective form of forecasting, investors should know that pro forma statements don't typically comply with generally accepted accounting principles (GAAP) . This is because pro forma statements don't include one-time expenses—such as equipment purchases or company relocations—which allows for greater accuracy because those expenses don't reflect a company’s ongoing operations.

7 Financial Forecasting Methods

Pro forma statements are incredibly valuable when forecasting revenue, expenses, and sales. These findings are often further supported by one of seven financial forecasting methods that determine future income and growth rates.

There are two primary categories of forecasting: quantitative and qualitative.

Quantitative Methods

When producing accurate forecasts, business leaders typically turn to quantitative forecasts , or assumptions about the future based on historical data.

1. Percent of Sales

Internal pro forma statements are often created using percent of sales forecasting . This method calculates future metrics of financial line items as a percentage of sales. For example, the cost of goods sold is likely to increase proportionally with sales; therefore, it’s logical to apply the same growth rate estimate to each.

To forecast the percent of sales, examine the percentage of each account’s historical profits related to sales. To calculate this, divide each account by its sales, assuming the numbers will remain steady. For example, if the cost of goods sold has historically been 30 percent of sales, assume that trend will continue.

2. Straight Line

The straight-line method assumes a company's historical growth rate will remain constant. Forecasting future revenue involves multiplying a company’s previous year's revenue by its growth rate. For example, if the previous year's growth rate was 12 percent, straight-line forecasting assumes it'll continue to grow by 12 percent next year.

Although straight-line forecasting is an excellent starting point, it doesn't account for market fluctuations or supply chain issues.

3. Moving Average

Moving average involves taking the average—or weighted average—of previous periods⁠ to forecast the future. This method involves more closely examining a business’s high or low demands, so it’s often beneficial for short-term forecasting. For example, you can use it to forecast next month’s sales by averaging the previous quarter.

Moving average forecasting can help estimate several metrics. While it’s most commonly applied to future stock prices, it’s also used to estimate future revenue.

To calculate a moving average, use the following formula:

A1 + A2 + A3 … / N

Formula breakdown:

A = Average for a period

N = Total number of periods

Using weighted averages to emphasize recent periods can increase the accuracy of moving average forecasts.

4. Simple Linear Regression

Simple linear regression forecasts metrics based on a relationship between two variables⁠: dependent and independent. The dependent variable represents the forecasted amount, while the independent variable is the factor that influences the dependent variable.

The equation for simple linear regression is:

Y ⁠ = Dependent variable⁠ (the forecasted number)

B = Regression line's slope

X = Independent variable

A = Y-intercept

5. Multiple Linear Regression

If two or more variables directly impact a company's performance, business leaders might turn to multiple linear regression . This allows for a more accurate forecast, as it accounts for several variables that ultimately influence performance.

To forecast using multiple linear regression, a linear relationship must exist between the dependent and independent variables. Additionally, the independent variables can’t be so closely correlated that it’s impossible to tell which impacts the dependent variable.

Qualitative Methods

When it comes to forecasting, numbers don't always tell the whole story. There are additional factors that influence performance and can't be quantified. Qualitative forecasting relies on experts’ knowledge and experience to predict performance rather than historical numerical data.

These forecasting methods are often called into question, as they're more subjective than quantitative methods. Yet, they can provide valuable insight into forecasts and account for factors that can’t be predicted using historical data.

6. Delphi Method

The Delphi method of forecasting involves consulting experts who analyze market conditions to predict a company's performance.

A facilitator reaches out to those experts with questionnaires, requesting forecasts of business performance based on their experience and knowledge. The facilitator then compiles their analyses and sends them to other experts for comments. The goal is to continue circulating them until a consensus is reached.

7. Market Research

Market research is essential for organizational planning. It helps business leaders obtain a holistic market view based on competition, fluctuating conditions, and consumer patterns. It’s also critical for startups when historical data isn’t available. New businesses can benefit from financial forecasting because it’s essential for recruiting investors and budgeting during the first few months of operation.

When conducting market research, begin with a hypothesis and determine what methods are needed. Sending out consumer surveys is an excellent way to better understand consumer behavior when you don’t have numerical data to inform decisions.

Improve Your Forecasting Skills

Financial forecasting is never a guarantee, but it’s critical for decision-making. Regardless of your business’s industry or stage, it’s important to maintain a forward-thinking mindset—learning from past patterns is an excellent way to plan for the future.

If you’re interested in further exploring financial forecasting and its role in business, consider taking an online course, such as Financial Accounting , to discover how to use it alongside other financial tools to shape your business.

Do you want to take your financial accounting skills to the next level? Consider enrolling in Financial Accounting —one of three courses comprising our Credential of Readiness (CORe) program —to learn how to use financial principles to inform business decisions. Not sure which course is right for you? Download our free flowchart .

About the Author

• Search Search Please fill out this field.

What Is Forecasting?

How forecasting works, forecasting techniques, choosing the right forecasting method, the bottom line.

• Technical Analysis
• Technical Analysis Basic Education

Forecasting: What It Is, How It’s Used in Business and Investing

Forecasting is a technique that uses historical data as inputs to make informed estimates that are predictive in determining the direction of future trends.

Businesses utilize forecasting to determine how to allocate their budgets or plan for anticipated expenses for an upcoming period of time. This is typically based on the projected demand for the goods and services offered.

Key Takeaways

• Forecasting involves making predictions about the future.
• In finance, forecasting is used by companies to estimate earnings or other data for subsequent periods.
• Traders and analysts use forecasts in valuation models, to time trades, and to identify trends.
• Forecasts are often predicated on historical data.
• Because the future is uncertain, forecasts must often be revised, and actual results can vary greatly.

Theresa Chiechi / Investopedia

Investors utilize forecasting to determine if events affecting a company, such as sales expectations, will increase or decrease the price of shares in that company. Forecasting also provides an important benchmark for firms, which need a long-term perspective of operations.

Equity analysts use forecasting to extrapolate how trends, such as gross domestic product (GDP) or unemployment , will change in the coming quarter or year. Finally, statisticians can utilize forecasting to analyze the potential impact of a change in business operations. For instance, data may be collected regarding the impact of customer satisfaction by changing business hours or the productivity of employees upon changing certain work conditions. These analysts then come up with earnings estimates that are often aggregated into a consensus figure. If actual earnings announcements miss the estimates, it can have a large impact on a company’s stock price.

Forecasting addresses a problem or set of data. Economists make assumptions regarding the situation being analyzed that must be established before the variables of the forecasting are determined. Based on the items determined, an appropriate data set is selected and used in the manipulation of information. The data is analyzed, and the forecast is determined. Finally, a verification period occurs when the forecast is compared to the actual results to establish a more accurate model for forecasting in the future.

The further out the forecast, the higher the chance that the estimate will be inaccurate.

In general, forecasting can be approached using qualitative techniques or quantitative ones. Quantitative methods of forecasting exclude expert opinions and utilize statistical data based on quantitative information. Quantitative forecasting models include time series methods, discounting, analysis of leading or lagging indicators, and econometric modeling that may try to ascertain causal links.

Qualitative Techniques

Qualitative forecasting models are useful in developing forecasts with a limited scope. These models are highly reliant on expert opinions and are most beneficial in the short term. Examples of qualitative forecasting models include interviews, on-site visits, market research , polls, and surveys that may apply the Delphi method (which relies on aggregated expert opinions).

Gathering data for qualitative analysis can sometimes be difficult or time-consuming. The CEOs of large companies are often too busy to take a phone call from a retail investor or show them around a facility. However, we can still sift through news reports and the text included in companies’ filings to get a sense of managers’ records, strategies, and philosophies.

Time Series Analysis

A time series analysis looks at historical data and how various variables have interacted with one another in the past. These statistical relationships are then extrapolated into the future to generate forecasts along with confidence intervals to understand the likelihood of the actual outcomes falling within that scope. As with all forecasting methods, success is not guaranteed.

The  Box-Jenkins Model is a technique designed to forecast data ranges based on inputs from a specified time series. It forecasts data using three principles:  autoregression , differencing, and  moving averages . Another method, known as  rescaled range analysis , can be used to detect and evaluate the amount of persistence, randomness, or  mean reversion  in time series data. The rescaled range can be used to extrapolate a future value or average for the data to see if a trend is stable or likely to reverse.

Most often, time series forecasts involve trend analysis, cyclical fluctuation analysis, and issues of seasonality .

Econometric Inference

Another quantitative approach is to look at cross-sectional data to identify links among variables—although identifying causation is tricky and can often be spurious. This is known as econometric analysis , which often employs regression models . Techniques such as the use of instrumental variables, if available, can help one make stronger causal claims.

For instance, an analyst might look at revenue and compare it to economic indicators such as inflation and unemployment. Changes to financial or statistical data are observed to determine the relationship between multiple variables. A sales forecast may thus be based on several inputs such as aggregate demand, interest rates, market share, and advertising budget (among others).

The right forecasting method will depend on the type and scope of the forecast. Qualitative methods are more time-consuming and costly but can make very accurate forecasts given a limited scope. For instance, they might be used to predict how well a company’s new product launch might be received by the public.

For quicker analyses that can encompass a larger scope, quantitative methods are often more useful. Looking at big data sets, statistical software packages today can crunch the numbers in a matter of minutes or seconds. However, the larger the data set and the more complex the analysis, the pricier it can be.

Thus, forecasters often make a sort of cost-benefit analysis to determine which method maximizes the chances of an accurate forecast in the most efficient way. Furthermore, combining techniques can be synergistic and improve the forecast’s reliability.

What is business forecasting?

Business forecasting tries to make informed guesses or predictions about the future state of certain business metrics such as sales growth or economy-wide predictions such as gross domestic product (GDP) growth in the next quarter. Business forecasting relies on both quantitative and qualitative techniques to improve accuracy. Managers use forecasting for internal purposes to make capital allocation decisions and determine whether to make acquisitions, expand, or divest. They also make forward-looking projections for public dissemination such as earnings guidance .

What are some limitations of forecasting?

The biggest limitation of forecasting is that it involves the future, which is fundamentally unknowable today. As a result, forecasts can only be best guesses. While there are several methods of improving the reliability of forecasts, the assumptions that go into the models, or the data that is inputted into them, has to be correct. Otherwise, the result will be garbage in, garbage out. Even if the data is good, forecasting often relies on historical data, which is not guaranteed to be valid into the future, as things can and do change over time. It is also impossible to correctly factor in unusual or one-off events like a crisis or disaster.

What are the forecasting techniques?

There are several forecasting methods that can be broadly segmented as either qualitative or quantitative. Within each category, there are several techniques at one’s disposal.

• Under qualitative methods, techniques may involve interviews, on-site visits, the Delphi method of pooling experts’ opinions, focus groups, and text analysis of financial documents, news items, and so forth.
• Under quantitative methods, techniques generally employ statistical models that look at time series or cross-sectional data, such as econometric regression analysis or causal inference (when available).

Forecasts help managers, analysts, and investors make informed decisions about the future. Without good forecasts, many of us would be in the dark and resort to guesses or speculation. By using qualitative and quantitative data analysis, forecasters can get a better handle of what lies ahead.

Businesses use forecasts and projections to inform managerial decisions and capital allocations. Analysts use forecasts to estimate corporate earnings for subsequent periods. Economists may make more macro-level forecasts as well, such as predicting GDP growth or changes to employment. However, since we cannot definitively know the future, and since forecasts often rely on historical data, their accuracy will always come with some room for error—and, in some cases, may end up being way off.

International Monetary Fund. " What Is Econometrics? "

• Terms of Service
• Editorial Policy
• Privacy Policy
• Your Privacy Choices

A Straightforward Guide to Qualitative Forecasting

Published: June 14, 2023

In sales, numbers are key, but they don't always give you a comprehensive picture of your org's performance and potential — particularly in forecasting. So while you can't ignore quantitative forecasting, you still need to consider factors beyond those hard figures for a thorough understanding. That’s where qualitative forecasting comes in.

Qualitative forecasting accounts for the more subjective elements of sales. By accounting for both sides of the forecasting process, you can put yourself in the best position to set accurate targets, plan for the future, and predict the success of your upcoming campaigns.

Here, we'll take a closer look at qualitative forecasting as a concept, review some methods and techniques you can use to get the most out of the process, see some examples of what it looks like in practice, and weigh its pros and cons. Let's jump in!

Table of Contents

• What is qualitative forecasting?

Benefits of Qualitative Forecasting

Qualitative forecasting methods and techniques, qualitative forecasting examples, advantages of qualitative forecasting, drawbacks of qualitative forecasting, what is qualitative forecasting.

Qualitative forecasting is a type of forecasting that involves more subjective, intuitive, or experiential approaches. It could revolve around elements like knowledge of a business's customer journey, market research, or company leadership's personal experience in a field.

There's no denying that numbers are a crucial part of any sales forecast — you should never try to put one together without them. But as touched on earlier, hard figures can't always give you a complete enough picture to inform an accurate forecast.

Qualitative forecasting fleshes out a more thorough understanding of customer and market behavior — helping businesses account for more angles and potential curveballs when conducting their sales efforts over a fixed period.

Qualitative forecasting helps when companies explore new sales methods or expect sales to deviate from the typical results. As companies grow, they might find themselves in uncharted territory — setting unprecedented goals and making plans they're not well-acquainted with. Here's why qualitative forecasting is so important in those situations.

Alt: Benefits of Qualitative Forecasting. Uses leading indicators instead of lagging indicators. Accounts for more variables. Uncovers expert insights.IMG name: qualitative-forecasting-benefits

Qualitative forecasting uses leading indicators instead of lagging indicators.

A study by Gong highlighted that while 63% of sales professionals considered sales forecasting extremely critical to the success of their business, only 27% said that it produces accurate results.

Forecasting based purely on historical data doesn't account for economic fluctuation, upcoming technologies, or unexpected market trends. In times of unprecedented change, qualitative forecasting accounts for external market conditions and helps you anticipate the impact of a given variable on your sales cycle — rather than trying to identify its consequences in hindsight.

Qualitative forecasting accounts for more variables.

Quantitative forecasting is traditionally limited to measurable objectives like revenue, customers, and product units sold. But qualitative forecasting is more expansive — it considers subjective elements like customer satisfaction, brand perception, and employee engagement.

Including those less tangible variables helps you anticipate the demand for your products or services in a given market — providing better insight into how much effort you need to put into a campaign and where your focus should lie.

Qualitative forecasting uncovers expert insights.

Armed with the right qualitative data, you can draw on the experience and knowledge of industry experts to inform your decisions. Use their firsthand insights to anticipate customer behaviors and better understand what needs to be done to move forward.

Qualitative forecasting helps you identify where there might be potential gaps between expectations and reality — helping you make more meaningful and informed decisions.

So how do you approach qualitative forecasting? There are several ways to go down this path.

Alt: Qualitative Forecasting Methods. Experience (Executive Opinion). Qualitative Forecasting Methods. Consultancy. Delphi Method. Surveys. Market Research. Sales Force Composite. IMG name: qualitative-forecasting-methods

1. Experience (Executive Opinion)

In many cases, some of the necessary insight and information to inform effective qualitative forecasting can come from within the company — typically from leadership.

Managers (or occasionally regular employees) might already have extensive knowledge of or experience with a certain market, product, or customer base. In those instances, they can be an excellent resource for assisting with qualitative forecasting.

2. Consultancy

Not every business has leadership seasoned enough to put together reliable qualitative forecasts based on personal experience — especially if a company is younger and scaling.

That's why companies often outsource their qualitative forecasting responsibilities to third parties. Consultants with a more developed pulse on an industry, market, or customer persona can be an excellent resource for a company struggling with qualitative forecasting.

3. Delphi Method

The Delphi Method is similar to the ones listed above in that it relies on experts, but the process is a bit more elaborate and sophisticated than most others. Instead of just asking experienced managers or consultants for their opinions off-hand or collaboratively, the method involves questioning multiple parties about a sales forecast separately to prevent groupthink.

The risk you run when leveraging the Delphi Method is a lack of consensus. If too many experts offer varying perspectives, it can be hard to piece together a cohesive, accurate qualitative forecast.

Surveys are another way to inform thoughtful, effective qualitative forecasting. This method is one of the more tried-and-true, relatively accessible options listed here. Hearing directly from your target audience helps you tailor a forecast backed by firsthand qualitative insight.

A well-constructed survey gives you insight into new markets, helps you understand shifting tides within your industry, and allows you to identify your customers' collective tendencies better. With several applications to create and distribute surveys at your disposal, this method is worth considering when putting together qualitative forecasts.

5. Market Research

When a business plans to enter a new market, it can use market research to boost its qualitative forecasting. This practice helps a company determine if breaching a new market is worth the effort and resources.

It also offers perspective on what potential new customers are looking for from the business. Resources like focus groups, product testing surveys, and polls can all be used when leveraging this method.

6. Sales Force Composite

Your sales team interacts with your customers more closely than anyone else and possesses a wealth of firsthand knowledge about customers’ buying habits.

The sales force composite forecasting method draws the insights of salespeople, sales management, and other channel members to produce sales forecasts. Train salespeople on how to forecast accurately, explicitly emphasize the importance of this market intelligence, and regularly review the data they provide to control the quality of your forecasting.

Virtually any significant decision any business makes can benefit from qualitative forecasting techniques.

When a company is either just starting or getting off the ground, its leadership will likely need to account for market research to determine if its idea, offering, business model, messaging, pricing, and marketing are viable.

In those cases, the organizations in question don't have existing numerical data to analyze and rely on — making accurate quantitative forecasting nearly impossible. Instead, those companies have to take different, more creative roads to produce a solid picture of what they can expect from their sales efforts and target prospects.

Qualitative forecasting is also an asset for more mature companies looking to release a new product or service. Quantitative methods can only get you far if you've never sold a specific offering. That's why businesses in this position generally look beyond those strategies to accurately understand what's to come.

Scenario 1: Launching a New Product

A tech giant like Samsung wants to introduce a new smartphone. Apple is the current market leader, and Samsung hopes this new product, which revolutionizes the OS, will give them an edge.

The problem is the global economy is heading into a recession, and this smartphone is 1.5x the price of its competitors. Samsung wants to gauge whether this new product is a wise financial decision and whether customers have the purchasing power to make it worthwhile.

The company can't rely on quantitative forecasting alone since inflation has risen in the past two months, and it might not be the best time to launch. Samsung turns to market research to understand how much customers are planning to spend on tech in the next quarter and how they perceive the value of their new, revolutionary product.

Scenario 2: Expanding Into a New Market

A mass fashion retailer like Zara wants to expand into the East Asian market and produce clothes representing local culture. It doesn't want to risk committing a faux pas by wrongly representing local trends, so it turns to qualitative forecasting.

The company looks for local influencers, surveys customers in the new market, and runs focus groups to get an accurate representation of what people want. It learns that launching a new brand instead of marketing existing products is the way to go and that locals respond better to combining traditional and modern elements.

A majority East Asian team is also a better way to approach this expansion since locals are more likely to trust the brand if people from their own culture represent it.

For some sales leaders, using anything besides numerical analysis in sales forecasting can seem intimidating or pointless — but qualitative forecasting offers several advantages that extend beyond those of its quantitative counterpart.

Qualitative forecasting provides relevance and flexibility.

Qualitative forecasting doesn’t care about last year’s sales numbers. Instead, it does care about more timely, relevant information, such as new technology your business has adopted or global trends that may affect the economy.

Qualitative forecasting takes non-numerical events and assigns weight to how they might impact a company's performance and operations — offering that business higher flexibility in its decision-making when those variables take hold.

Qualitative forecasting gives you a broader perspective.

When paired with quantitative forecasting, qualitative forecasting can give a company a holistic look at virtually every factor — both objective and subjective — when considering a significant decision.

This point is particularly relevant to larger companies with historical numerical data and the resources to supplement it with internal or external expertise and market research. With the ability to deliver on both sides of the forecasting token, these businesses can reliably make comprehensive, accurate sales predictions.

Qualitative forecasting works particularly well for new and growing companies.

While larger enterprises likely have reliable quantitative data to pair with qualitative insight, startups, and small businesses might not be so lucky. In most cases, those companies haven't been around long enough to accrue a significant bank of hard sales figures — making qualitative data central to their forecasts.

Though qualitative forecasting has tremendous upsides, it still comes with its fair share of drawbacks.

Qualitative forecasting can be compromised by bias.

Whether a company turns to skilled employees, consultants, or customer insights, it risks compromising insight with bias. Qualitative data is inherently subjective, and subjective information is naturally prone to bias.

Qualitative forecasting is prone to inaccuracy.

Without definite numbers to rely on, qualitative data can produce incorrect results due to manual errors. This point ties into the one above — biased data is generally naturally inaccurate.

For instance, a customer might respond to a survey or poll a business is running to vent about a single negative experience. Or, a manager relying on past experiences to inform forecasts might bring too personal a spin to the process or see past events and trends through a warped lens.

Qualitative forecasting might be invalid.

Hired consultants or expert panels outside the business can provide a different perspective, but their separation from the company could render their forecasts invalid. Companies turning to subjective insights risk receiving illegitimate or irrelevant forecasts.

Alt: Qualitative forecasting pros and cons. Advantages. Provides relevance and flexibility. Gives you a broader perspective. Works well for new and growing companies. Disadvantages. Can be compromised by bias. Is prone to inaccuracy. Might be invalid.IMG name: qualitative-forecasting-pros-cons

Use Qualitative Forecasting for Improved Decision-Making

Any time a business needs to make a decision or step forward, it needs a comprehensive forecast to help set goals, milestones, and expectations. Data analysis can always help guide a business, but quantitative data doesn’t always provide the whole picture.

That’s why qualitative forecasting is so important. It can provide deeper insight that considers varying viewpoints, experiences, and real-world events, letting a company be as prepared as possible to move forward effectively.

Don't forget to share this post!

Related articles.

9 Strategic Planning Models and Tools for the Customer-Focused Business

S&OP: A Comprehensive Overview of Sales and Operations Planning

4 Clever and Effective Ways to Simplify Your Sales Process From Seasoned Sales Experts

How to Develop a Strategic Plan for Business Development [Free Template]

Lead Distribution Methods and Best Practices

Lead Routing: How to Precisely Implement and Route Key Prospects

The 25 Best Lead Distribution Software in 2022

Return on Sales: How to Calculate It and What You Need to Know

30 Key Interview Questions and Answers for Sales Operations Role

How Using a Document Library Can Improve Your Sales Process

Outline your company's sales strategy in one simple, coherent plan.

Powerful and easy-to-use sales software that drives productivity, enables customer connection, and supports growing sales orgs

Machine Learning for New Product Forecasting

• First Online: 21 September 2023

Cite this chapter

• Mohsen Hamoudia 5 &
• Lawrence Vanston 6  

Part of the book series: Palgrave Advances in the Economics of Innovation and Technology ((PAEIT))

451 Accesses

1 Citations

Forecasting the demand for new products is crucial given the level of investment required for a launch. It is also challenging and risky in an environment of vigorous economic competition, evolving customer expectations, and the emergence of new technologies and innovations. Given the high failure rate of new launches (70–80 percent for consumer-packaged goods), the accuracy of demand forecasts is a top priority for decision-makers. Underpredicting demand leads to a loss of potential sales; overpredicting it leads to costly excess inventory.

Forecasting new product demand has traditionally been done using a variety of techniques: judgmental methods, market research like surveys of buyers’ intentions, market testing, expert opinion methods like the Delphi method, diffusion models like the Bass model, and statistical modeling through a variety of time series and/or multivariate techniques. More recently, machine learning has been added to the mix. The selection depends somewhat on whether the new product is: (a) new to the world, (b) new to the firm, (c) an addition to existing product lines, or (d) an improvement or revision to existing products.

Machine learning is a good candidate when we have lots of data, including the sales history, on existing products that are similar to the new one. Although humans use this approach too, the idea is that machine learning should be able to do it faster and more accurately. Many papers and case studies are available on using machine learning to forecast existing products with historical data. However, when it comes to new products with little or no history, the literature is very limited.

In this chapter, we will review the main techniques for predicting new product demand, focusing on machine learning. We also review four recent case studies that confirm that machine learning can improve accuracy of demand forecasts for new products.

• Forecasting
• Machine Learning
• New Products
• Diffusion Models

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

• Available as PDF
• Read on any device
• Instant download
• Own it forever
• Available as EPUB and PDF
• Durable hardcover edition
• Dispatched in 3 to 5 business days
• Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Armstrong, J. S. (2004). Principles of forecasting—A handbook for researches and practitioners . Kluwer Academic Publishers.

Google Scholar  

Bass, F. M. (1969). A new product growth for model consumer durables. Management Science, 15 , 215–227.

Article   Google Scholar  

Bass, F. M., Trichy, V. K., & Dipak, C. J. (1994, Summer). Why the bass model fits without decision variables. Marketing Science, 13 (3), 203–223.

Benidis, K., Rangapuram, S. S., Flunkert, V., Wang, Y., Maddix, D., Turkmen, C., Gasthaus, J., Bohlke-Schneider, M., Salinas, D., Stella, L., & Aubet, F. X. (2022). Deep learning for time series forecasting: Tutorial and literature survey. ACM Computing Surveys, 55 (6), 1–36.

Bishop, C. M. (2006). Pattern recognition and machine learning (p. 657). Springer.

Gilliland, M., Tashman, L., & Sglavo, U. (2015). Business Forecasting, J. Wiley & Sons, Inc.

Hamoudia M. (2021). Forecasting new products using statistical methods vs machine learning, IIF Workshop, Madrid, Spain, 9 December 2021.

Hastie, T., Tibshirani, R., & Friedman, J. (2001). The elements of statistical learning: Data mining, inference, and prediction (p. 361). Springer.

Book   Google Scholar  

Hielkrem, C. (2008). Market scenarios and conjoint analysis, in Telektronikk, 3 / 4.08.

Januschowski, T., Wang, Y., Torkkola, K., Erkkilä, T., Hasson, H., & Gasthaus, J. (2022). Forecasting with trees. International Journal of Forecasting, 38 (2022), 1473–1481.

Jeffrey, R., Song, T. M., & Calantone, R. J. (2000, November). Artificial neural network decision support systems for new product development project selection. Journal of Marketing Research, 37 (4), 499–507 (9 pages). Sage Publications, Inc.

Kosina, L. (2017, May 3). Post, What percentage of new products fail and why? https://www.publicity.com/marketsmart-newsletters/percentage-new-products-fail/

Kunz, M., Birr, S., Raslan, M., Ma, L., & Januschowski, T. (2023). Deep learning based forecasting: A case study from the online fashion industry, Chapter 11 In Forecasting with artificial intelligence: Theory and applications . Plagrave.

Lee, H., Kim, S. G., Park, H. W., & Kang, P. (2014). Pre-launch new product demand forecasting using the Bass model: A statistical and machine learning-based approach. Technological Forecasting and Social Change, 86 (2014), 49–64.

Loureiro, A., Miguéis, V., & Da Silva, L. F. (2018). Exploring the use of deep neural networks for sales forecasting in fashion retail. Decision Support System, 114 (2018), 81–93.

Luellen, E. (2020, July). Post the top five machine learning methods to forecast demand for new products, in towards data science. https://towardsdatascience.com/the-top-five-machine-learning-methods-to-forecast-demand-for-new-products-b881ac7e3f32

Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2022). M5 accuracy competition: Results, findings, and conclusions. International Journal of Forecasting . https://doi.org/10.1016/j.ijforecast.2021.11.013

Makridakis S., Spiliotis S., & Assimakopoulos V. (2018). Statistical and Machine Learning forecasting methods: Concerns and ways forward, Computer Science, Medicine.

Makridakis, S., Wheelwright, S. C., & McGee, V. E. (1983). Forecasting—Methods and Applications, 2nd Edition. Wiley.

Mas-Machuca M., Sainz M., & Martinez-Costa C. (2014). A review of forecasting models for new products. Intangible Capital, 10 (1).

Meade, N., & Al. (2000). Modelling diffusion and replacement. European Journal of Operational Research, 125 , 551–570.

Meade, N. (1984, October/December). The use of growth curves in forecasting market development—a review and appraisal. Journal of Forecasting .

Menon S., & Ranjan R. (2020). Post The evolution of forecasting techniques: Traditional versus machine learning methods. https://www.genpact.com/insight/the-evolution-of-forecasting-techniques-traditional-versus-machine-learning-methods

Ord K., Fildes R., & Kourentzes N. (2017). Principles of Business Forecasting, 2nd Edition. Wessex Press Inc.

Schaer, O., Kourentzes N., & Fildes R. (2022, May). Predictive competitive intelligence with pre-release online search traffic. Production and Operations Management, 31 (4).

Semenoglou A., Spiliotis E., Makridakis S., & Assimakopoulos V. (2021, July–September). Investigating the accuracy of cross-learning time series forecasting methods. International Journal of Forecasting, 37 (3), 1072–1084.

Semenoglou, A., Spiliotis, E., & Assimakopoulos, V., (2023). Neural network ensembles for univariate time series forecasting. Forecasting with Artificial Intelligence—Theory and Applications . Palgrave.

Singh P. K., Gupta Y., Jha N., Rajan A. (2019): Fashion Retail: Forecasting Demand for New Items, arXiv preprint arXiv:1907.01960.

Smirnov P. S., & Sudakov V. A. (2021). Forecasting new product demand using machine Learning 2021. Journal of Physics: Conference Series 1925 012033.

Sokele, M. (2008). Growth models for the forecasting of new product market adoption, in Telektronikk, 3 / 4.08. https://nastava.tvz.hr/kirt/wp-content/uploads/sites/4/2016/11/Telektronikk-2008.pdf

Thomassey, S., & Fiordaliso, A. (2006). A hybrid sales forecasting system based on clustering and decision trees. Decision Support Systems, 42 (2006), 408–421.

Thomassey, S., & Happiette, M. (2007). A neural clustering and classification system for sales forecasting of new apparel items. Applied Soft Computing, 7 (2007), 1177–1187.

University of Minnesota. (2016). Exploring Business. Author removed at request of original publisher. University of Minnesota Libraries Publishing, Edition 2016. https://open.lib.umn.edu/exploringbusiness/and https://open.lib.umn.edu/exploringbusiness/chapter/10-1-what-is-a-product/

Van Steenbergen R. M., & Mes M. R. K. (2020, December). Forecasting demand profiles of new products. Decision Support Systems, 139 .

Vanston, L. (2008). Practical tips for forecasting new technology adoption, Telektronikk 3/4.2008. http://tfi.com/pubs/forecastingtips.pdf

Vanston, L., & Hodges, R. (2004). Technology forecasting for telecommunications. Telektronikk, 100 (4), 32–42. http://tfi.com/pubs/w/pdf/telektronikk_peer.pdf

Vanston, L., Rodgers C., & Hodges, R. (1995). Advanced video services—Analysis and forecasts for terrestrial service providers. Technology Futures, Inc., p. 106.

Wright, M. J., & Stern, P. (2015). Forecasting new product trial with analogous series. Journal of Business Research, 68 (2015), 1732–1738.

Download references

Acknowledgements

We would like to thank Evangelos Spilotis (National Technical University of Athens, Greece) and Robert Fildes (Centre for Marketing Analytics and Forecasting Lancaster University Management School, United Kingdom) for reviewing our article and Robert Van Steenbergen for allowing us use two tables contained in this article (R. M. Van Steenbergen, M. R. K. Mes, 2020 ).

Author information

Authors and affiliations.

France Telecom Group (Orange) and PREDICONSULT, Paris, France

Mohsen Hamoudia

TFI, Austin, TX, USA

Lawrence Vanston

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Mohsen Hamoudia .

Editor information

Editors and affiliations.

France Telecom Group, Orange Business Services, Eragny, France

Institute For the Future (IFF), University of Nicosia, Engomi, Cyprus

Spyros Makridakis

School of Electrical and Computer Engineering, National Technical University of Athens, Zografou, Greece

Evangelos Spiliotis

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Hamoudia, M., Vanston, L. (2023). Machine Learning for New Product Forecasting. In: Hamoudia, M., Makridakis, S., Spiliotis, E. (eds) Forecasting with Artificial Intelligence. Palgrave Advances in the Economics of Innovation and Technology. Palgrave Macmillan, Cham. https://doi.org/10.1007/978-3-031-35879-1_4

Download citation

DOI : https://doi.org/10.1007/978-3-031-35879-1_4

Published : 21 September 2023

Publisher Name : Palgrave Macmillan, Cham

Print ISBN : 978-3-031-35878-4

Online ISBN : 978-3-031-35879-1

eBook Packages : Economics and Finance Economics and Finance (R0)

Share this chapter

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Publish with us

Policies and ethics

• Find a journal
• Track your research

What is Sales Forecasting? How to Forecast Sales

Sales forecasting is a very important part of the sales management process and can make a huge difference in an eCommerce business decision-making process. Similar to the way a weather forecast will help you know if you need to take the umbrella out, a sales forecast allows businesses, sales reps, and sales managers to align resources effectively.

Imagine you own a seafood restaurant in a popular coastal town. As the summer season approaches, it’s only logical that you’d want to estimate your sales for the upcoming months to ensure you have enough inventory, staff, and resources to meet customer demand. 

Key Takeaway: If you understand the principles of sales forecasting and how to forecast sales, you’ll be able to implement efficient business systems without breaking a sweat. You can generate a sales forecast that provides insights into anticipated revenue, peak hours, and busy periods. 

Easy, right?

Accurate forecasting involves analyzing historical data, considering external factors such as weather conditions and local events, and monitoring market trends and customer preferences. Armed with this knowledge, you can optimize your operations and maximize profitability during the bustling summer season.

Let’s look a little closer at what is sales forecasting.

What is a Sales Forecast?

A sales forecast is a prediction or estimate of future sales volumes, revenues, and other sales-related metrics for a specific period. It provides insights into anticipated customer demand and helps businesses plan and allocate resources effectively to meet that demand.

Now, it is important to note that sales forecasts are not guaranteed predictions but rather educated estimates based on available consumer data and assumptions. They serve as a valuable tool to guide business strategies and align operations, enabling organizations to adapt and respond to market dynamics effectively. 

What is Sales Forecasting?

Sales forecasting is the process of estimating or predicting future sales volumes, revenues, and other sales metrics and performance indicators over a specific period. Simply put, a sales forecast allows business owners to predict the number of products that the company will sell in the next week, month, quarter, or year. 

With an accurate sales forecast, you can optimize your inventory levels and improve operational efficiency. By accurately predicting future demand, you know when to restock, the products that are now dead stock , and the right time to cross-sell and upsell high-demand products .

Additionally, a sales forecast can help you minimize wastage, reduce carrying costs, and avoid stockouts or shortages. Efficient wholesale inventory management ensures timely product availability, enhances customer satisfaction , and improves overall operational efficiency.

So, how do you predict the future for your business? It’s simple!

Eager to unlock the secrets of how marketplace platforms like eBay, Amazon, and Etsy thrive? Learn the ins and outs of marketplace business models and discover strategies for your own successful online venture. 

From checking the data of past transactions to understanding current market trends, you can determine how well your products will do in the market. You can also use sales forecasting software, sales automation technology, artificial intelligence, machine learning, and other sales algorithms.

There are various types of sales forecasting. Due to the fact that sales forecast are unguaranteed predictions, businesses can use a combination of the different forecasting types.

Let’s look at some of the types of sales forecasting.

Types of Sales Forecasting

Here are some common types of sales forecasts:

• Time-Based Forecast: This type of sales forecast predicts sales over a specific time period, such as weekly, monthly, quarterly, or annually. It provides a high-level view of expected sales volumes and revenues during a defined time frame.
• Product-Based Forecast: A product-based forecast focuses on estimating sales for individual products or product categories. It helps businesses understand the demand for specific offerings and allocate resources accordingly. This forecast can be useful for inventory management, production planning, and assessing the performance of different product lines.
• Market-Based Forecast: A market-based forecast examines sales projections based on market segments, customer demographics, or geographical regions. It provides insights into the demand for products in different target markets and helps businesses tailor their marketing and eCommerce sales strategies accordingly.
• Industry-Based Forecast: An industry-based forecast considers the overall market trends and performance of the industry in which you operate. It takes into account factors such as industry growth rates, competitive dynamics, and market forces that may impact sales. This forecast will help you understand your position within the industry and make informed decisions regarding market share and growth opportunities.
• Opportunity-Based Forecast: An opportunity-based forecast focuses on estimating sales for specific opportunities, such as new product launches, entering new markets, or securing large contracts. You can easily assess the potential revenue and sales impact of specific business initiatives or strategic decisions.
• Territory-Based Forecast: A territory-based forecast looks at sales projections for specific sales territories or regions. It considers factors such as local market conditions, customer preferences, and sales team performance within each territory. This forecast can aid in territory management, sales target setting, and resource allocation across different geographic areas.

Sales Forecasting Methods: How to Forecast Sales

Before we continue, it is important that you remember that no forecasting method is foolproof, and it's crucial to consider multiple methods and sources of data to gain a comprehensive understanding of future sales. 

Let's explore some common sales forecasting methods:

Historical Sales Method

This method involves analyzing past sales data to identify patterns, trends, and seasonality in business . By examining historical sales performance for similar periods, you can make informed predictions about future sales. 

With relatively stable market conditions and a substantial sales history, you can use this sales forecast strategy for your business.

Market Research Method

Market research involves gathering data on customer preferences, market trends, and competitor analysis. By conducting surveys, interviews, or studying industry reports, you can gain insights into market demand and customer behavior. 

This method helps you understand the factors that influence sales and make forecasts based on market dynamics.

Expert Opinion Method

Seeking input from industry experts, sales professionals, or consultants can provide valuable perspectives on market trends and sales projections. If you lack historical customer data or need a qualitative perspective on market conditions, then this strategy is for you.

Time Series Analysis Method

Time series analysis involves examining historical sales data to identify patterns, trends, and seasonality. Statistical techniques, such as moving averages or exponential smoothing, are applied to forecast future sales based on these patterns. 

This method is effective for businesses with significant historical sales data and when sales patterns are relatively stable.

Lead Generation Method

This method involves analyzing leads, prospects, and eCommerce conversion rates to estimate future sales. By tracking and analyzing the sales pipeline, you can forecast sales based on the number and quality of leads entering the pipeline and the historical conversion rates. 

You can use this method if you have a well-defined sales funnel and a robust lead-tracking system.

Predictive Analytics Method

Predictive analytics leverages advanced technologies like artificial intelligence and machine learning to analyze large datasets and predict future sales. These algorithms can identify patterns, correlations, and predictive indicators that human analysis might miss. 

This method is suitable when you have access to vast amounts of data and want to leverage technology for accurate and data-driven forecasts.

Regression Analysis Method

Regression analysis uses statistical techniques to identify relationships between sales and various independent variables, such as advertising spend, pricing, or economic indicators. Applying regression models can help you estimate how changes in these variables impact future sales. 

This method is suitable when you have access to extensive historical data and want to quantify the impact of different factors on sales.

How to Forecast Sales For a New Product

Creating a sales forecasting model for a new product can be challenging as you don't have historical data to rely on. However, with a structured approach and careful analysis, you can still make informed predictions. 

Here are some steps to help you forecast sales for a new product:

• Market Research: Start by conducting thorough market research to understand your target market, customer needs, and competitors. Identify the size of the potential market, key demographics, buying behavior, and any existing demand for similar products. This information will provide a foundation for estimating your market share and potential sales.
• Define Sales Drivers: Identify the key factors that will drive sales for your new product. Consider aspects such as wholesale vs retail price , product features, eCommerce marketing campaigns, wholesale distribution channels, and any unique selling propositions . Determine how these drivers will influence customer demand and sales potential.
• Establish Assumptions: In the absence of historical data, you will need to make certain assumptions based on market research, industry knowledge, and expert opinions. Define these assumptions clearly, such as the expected market penetration rate, customer adoption rate, or the impact of wholesale marketing efforts. These assumptions will form the basis for your sales forecast.
• Develop Multiple Scenarios: Since forecasting for a new product involves uncertainties, it's beneficial to create multiple scenarios. Consider best-case, worst-case, and moderate scenarios based on different market conditions, competitive pressures, and customer acceptance. This approach allows you to gauge a range of possible outcomes and plan accordingly.
• Conduct Surveys or Focus Groups: Gather feedback from potential customers through surveys or focus groups to assess their interest, preferences, and willingness to purchase your new product. This qualitative data can provide insights into customer perception, potential demand, and pricing sensitivity.
• Utilize Expert Opinions: Seek input from industry experts, market analysts, or consultants who have experience in your product's market segment. Their insights can help validate your assumptions, offer additional perspectives, and enhance the accuracy of your sales forecast.
• Monitor Early Sales and Adjust: Once your new product is launched, closely monitor its initial b2b vs b2c sales performance. Track key metrics such as sales volume, customer feedback, and market response. Compare the actual results with your forecasted numbers and adjust your forecast as needed based on real-time data and insights gained from the market.
• Refine and Iterate: Sales forecasting is an iterative process. Continuously evaluate your forecast accuracy, learn from any deviations, and refine your forecasting methods over time. Incorporate actual sales data as you accumulate it, and adjust your assumptions and models to improve the accuracy of future sales forecasts.

Frequently Asked Questions About Sales Forecasting

From tracking your sales metrics like average sales cycle , win rate , average deal size , and customer churn rate to integrating the best sales rep software and reducing customer churn rate, managing sales and closing deals requires a lot of work. However, with a sales forecasting tools and sales management software , you can improve the sales efficiency of your sales pipeline .

Let's answer a few questions sales leaders may have about sales forecasting:

What are the steps in sales forecasting?

The steps in sales forecasting include the following:

• Gathering historical data
• Defining forecast period
• Selecting a forecasting method
• Preparing and analyzing data
• Applying the chosen forecast methods
• Validating and refining the forecast
• Monitoring and updating

What is the basis of sales forecast?

The basis of a sales forecast typically includes historical sales data, market research, customer behavior analysis, industry trends, economic indicators, and external factors that influence sales. It is important to consider both quantitative and qualitative information to develop a comprehensive and reliable sales forecast.

What are the 4 basic forecasting methods?

The four basic forecasting methods are:

• Time series analysis
• Market research and surveys
• Qualitative judgment
• Regression analysis

• Best SEO Tools
• Social Media Scheduling Tools
• Social Listening Tools
• Website Analytics Tools
• Rank Tracking Software
• Hashtag Generator Tools
• Paraphrasing Tools
• Reputation Management Software
• Email Marketing Software
• Free Email Marketing Services
• Email Tracking Software
• Email Newsletter Software
• Mass Email Services
• Email Verifier Tools
• Email Signature Generators
• Email Marketing Services
• Mailchimp Pricing
• ActiveCampaign Pricing
• Sendinblue Pricing
• GetResponse Pricing
• ConvertKit Pricing
• Constant Contact Pricing
• MailerLite Pricing
• Klaviyo Pricing
• What is Advertising?
• What is Affiliate Marketing?
• What is Omnichannel Marketing?
• What is Marketing Mix?
• What is Service Marketing?
• Important Marketing KPIs
• What is Integrated Marketing?
• Types of Market Segmentation
• Beginner’s Guide to SEO
• How to Increase Domain Authority
• Beginner’s Guide to Email Marketing
• Guide to Facebook Marketing
• Pricing Strategies Guide
• How to Define Target Audience
• How to Do Market Research

Demand Forecasting: Types, Methods, and Examples

Running a business is not a piece of cake. You have to know how every aspect of your business will turn out. There are a lot of calculations you have to get right from accounting to inventory management to financial projections.

Every business manager should have an understanding of the demand for your products. Demand forecasting is one of the toughest metrics to get right because of the tendency of demand to fluctuate.

In this guide, you will learn the meaning of demand forecasting, the importance of demand forecasting, types of demand forecasting, demand forecasting methods, factors that influence the customer demand life cycle, how to forecast demand effectively, and examples of demand forecasting.

Let’s get started.

What is Demand Forecasting?

Demand forecasting is the use of historical sales data to predict the future demand for a product or service. It provides an estimate of the number of goods or services expected to be demanded by customers within a given period in the future.

What current and future customers will want to buy is identified and purchase orders or manufacturing is optimized through this information.

Through demand forecasting, businesses also get to make informed decisions about their supply chain.

Estimates of total sales and revenue in the future are the main results of demand forecasting. With these, decisions about inventory planning, future warehouse management needs, and sales become easier to make and more accurate.

Important estimations in running a business are also dependent on demand forecasting. These include inventory turnover, cash flow, profit margins, risk management, and capacity planning, among others.

Demand forecasting is an area of predictive analytics in business and deals with the optimization of the supply chain and overall inventory management. The past records of demand for a product are compared with current market trends to come to an accurate estimation.

Every company wants to be able to predict the amount of cost it has to bear to meet the demands of its customers. Demand forecasting is one of the methods of doing this.

Importance of Demand Forecasting for Ecommerce Businesses

Demand is undoubtedly one of the most important, flexible, and fragile factors that determine the success of a business. Forecasting your demand helps you a lot with running a business. Here are some of the benefits of demand forecasting.

Easier To Make Decision

Demand forecasting facilitates important management activities within a company. Decisions are easier to make and, for instance, performance evaluations are given enough context.

Companies know how well the whole business, departments, or employees can cope with future expectations and make decisions accordingly.

Deciding how much resources are needed for future demands as well as whether a business is ready for expansion is also made easier. Companies have enough information to estimate and decide on financial and managerial needs for the future.

Helps With Short and Long-Term Planning

Proper demand forecasting helps businesses to easily take care of important strategic plans for the future.

Without knowledge of your demand, long-term business plans like budgeting, financial planning, and capacity planning, among others, are harder to create. These plans are also very much susceptible to inaccuracies and unproductivity.

Short and medium-term plans like contract creation and choosing a supplier are also difficult to make.

Demand forecasting gives businesses an idea of what to expect from customers within a period in the future. It helps managers set financial goals , create budgets, and allocate the company’s resources efficiently.

Reduces Cost

Proper knowledge of the expected future demand for goods and services enables businesses to avoid suffering massive losses or opportunity costs.

Costs of production, inventory purchase, and marketing are kept streamlined with estimated forecasts. With demand forecasting, profit margins are determined and financial resources are not overspent in a way that a profit margin is closed up.

Opportunity costs are also avoided. A company knows the opportunities for expansion or the potential for increased demand for goods in the future. Enough inventory is stocked in expectation for this demand and the amount of profit that would have been lost from a stock-out situation is saved.

The staff required to take care of demand is easily determinable through demand forecasts. You ensure that you have enough manpower to deal with demand and excess wage is not paid to staff you don't need.

Pricing Strategy Is Easily Determined

The demand for a product determines the pricing strategy or the price you put on it for profit.

Too much demand for a product without an adequate supply of it causes its price to increase. On the other hand, where the supply of a product becomes more than its demand, its price drops.

Demand forecasting takes this into account and determines the elasticity of demand as it relates to price. Prices are adequately determined according to future demands of goods.

Businesses use demand forecasting to ensure that they do not place prices that are too high for customers and too low for them to generate profits.

Types of Demand Forecasting

Demand forecasting is distinctly classified based on three different factors – the scope of the market considered (Macro and Micro-level demand forecasting), the number of details required (Passive and Active forecasting), and the length of time considered (Short-term and Long-term forecasting).

1. Micro-Level Demand Forecasting

Micro-level demand forecasting involves estimations concerning the internal operations of a business.

Demand forecasting at the microeconomic level is specific to a business and different segments of its internal operations. These segments may include particular product categories, customer groups, sales division, financial division, and other internal areas of business operations.

Micro-level demand forecasting also takes metrics like the cost of goods sold (COGS), cost of goods manufactured (COGM) , net profit, and internal cash flow into consideration, among others.

2. Macro-Level Demand Forecasting

Macro-level demand forecasting deals with the broader macro-economic environment. It deals with external economic conditions and factors that affect a company's demand.

Some of the different factors considered with macro-level forecasting include general market research, customer preference change, inventory portfolio expansion, and other external macro-economic factors.

3. Passive Demand Forecasting

Passive demand forecasting is common with more stable internal and external economic environments. It involves and requires only historical data to predict future demand for goods and services.

With stable economic environments, past demand metrics can be directly used to predict future demand. Demand is expected to be the same as previous accounting periods, so other activities like trend analysis and crude statistical calculations are averted.

Passive demand forecasting is a rare but good model for businesses that aim for stability rather than growth.

4. Active Demand Forecasting

Active demand forecasting is used by startups or companies aiming for business growth and expansion . It involves extended marketing research , the study of trends, multiple calculations, assumptions, and plans for promotional campaigns and business expansion.

External factors are the main focus of active demand forecasting. Some of the factors that are typically considered include economic outlook, general market growth projections, and supply chain studies.

Active demand forecasting is most especially important for startups that do not have historical data and are forced to rely on external factors.

5. Short-Term Demand Forecasting

Short-term demand forecasting is done with a period of 3 months to a year in mind. It considers the amount of demand that is expected within this short period. Short-term business decisions are made during this period.

6. Long-Term Demand Forecasting

Long-term demand forecasting deals with time lengths of between 12 months and possibly up to 4 years. It drives long-term business decisions regarding activities like financial planning, capital expenditure, and capacity investment planning, among a whole lot of others.

Understanding Demand Forecasting Methods

Before going on about demand forecasting, you need to know the different methods and which one is appropriate for you.

Some of the most popular and crucial methods in demand forecasting include the Delphi technique, conjoint analysis, intent survey, trend projection method, and econometric forecasting.

1. Delphi Technique

The Delphi method involves the use of a group of experts that provide their individual forecasts and justifications for their forecasts.

Each forecast and explanation is then read out to other experts on the panel, with each of them influenced by the forecast of their counterparts. A subsequent forecast is then made by each expert with the new influenced knowledge and this process repeats itself until a consensus is reached.

A consensus exists when there is no significant difference between the forecasts of the different experts.

The Delphi method is based on the idea that an individual cannot accurately or effectively predict future demands all on his or her own. When executed properly, the Delphi method is a very accurate technique of forecasting demands.

However, there are downsides to it. Apart from the need for highly knowledgeable experts on this panel to ensure accurate forecasts, the Delphi method is time-consuming.

2. Conjoint Analysis

The conjoint analysis involves the use of surveys to collect information about customer preferences as relating to a product.

Surveys are typically in the form of questionnaires that seek preference information from customers. Consumers are asked about what they think of a particular product attribute and businesses make forecasts from their answers.

Information that surveys target to get from customers falls into personal, demographic, and economic information.

Conducting surveys helps a company to realize the most important selling point of their different products and services. The reasons why consumers choose a certain product over others is identified and a company gets to know which product or service feature consumers value the most.

Conjoint Analysis is a good demand forecasting method for products with no history. When a company wants to enter into another product category or increases its inventory portfolio, information about the preferred attributes allows it to start on the right track.

Market preference and how consumers react to a product are collected and used accordingly.

3. Intent Survey

An intent survey aims to collect information about which product consumers are intending to buy in the future. This technique aims at understanding the factors that push a consumer to buy a product.

Intent surveys are usually conducted through the websites of companies and typically ask website visitors to rate their intent to buy a product on a scale of 0 – 10.

Where intent is rated high, a company then decides on whether it should proceed to stock a product it was previously considering.

One point to note is that intent surveys only predict the likelihood of a product being purchased and not the actual consumer behavior. It is also better used to predict the purchase of existing products, durable products, and short-term forecasting periods.

4. Trend Projection Method

The trend projection method is effective for companies with large historical sales data. This sales data history typically spans more than 18 – 24 months.

A time series representing the past sales and demand for a particular product is then formulated. These different graphical trends are followed closely and used to determine the expected future demand for products.

From the above, it is apparent that the trend projection method is only effective and feasible in generally stable economic environments. Uncertain environments usually do not have consistent graphical patterns over this long period and, therefore, are not effective to use.

5. Econometric Forecasting

Econometric forecasting involves the use of mathematical equations and various variables to come up with a demand forecast. It uses relationships among economic variables to forecast future developments.

Factors Influencing the Customer Demand Life Cycle

Demand forecasting is all about how the supply chain meets the demand for products. Numerous factors are influencing the customer demand life cycle such as seasonality, external competition, type of product, and geographical location.

1. Seasonality

Seasonality refers to the change in demand for products over a particular period . It involves the different periods and the volume of orders that are characteristic of them.

A company that runs a highly seasonal business typically records highly distinct demand trends throughout the year . Demands are only received in a specific period or several limited periods of the year. Due to this, graphical demand trends show a spike in this period.

An example would be a company that manufactures and sells Christmas apparel. Demand for Christmas apparel is majorly received towards the end of the year, with a peak period in December.

Seasonality requires a company to optimize inventory storage following the expected demand trends.

Inventory items and staff are kept very low during quiet periods while purchase orders, manufacturing activities, and inventory storage intensify towards periods of demand spikes.

2. External Competition

One unavoidable aspect of running a business is the competition for the attention of customers. The more competition you have in the market, the more options your potential consumers have to choose from other than you.

With a lot of activities by external competitors to get the attention of consumers, the demand for your products will remain inconsistent and continuously dwindling. The effect of this factor is most especially noticeable when a new competitor comes into the market.

Competitor strategies largely affect how demand for a product shapes out to be and companies consider this while forecasting.

3. Type of Product

The demand forecast of a product is different from the forecast for other products. Each product has its own market peculiarities and, therefore, should be given distinct attention.

Perishable goods have separate market characteristics as opposed to durable goods. Services that are paid for at the end of a monthly cycle are also different from services with spontaneous payment cycles.

Nonetheless, no matter what a product or service is, certain factors are crucial for consideration. These include the lifetime and purchase value of your customers for each product as well as the combination of products that are typically ordered.

Taking these into account helps you understand how you can group or bundle products and how the demand for one inventory item affects the demand for another.

4. Geographical Location

The location where you operate greatly determines both the demand for your products and how you meet up with demands.

A lot of consumers prefer to buy items that can be immediately shipped to where they reside. Due to this, the location where your inventory is stored is very important.

Order fulfillment centers can be placed at strategic locations that allow orders to be delivered quickly. You can also use reliable order fulfillment services to help you fulfill your products if your business does not have the resources to handle them.

With demand easily met and orders quickly fulfilled, consumers are encouraged to keep purchasing products.

Bad geographical locations greatly hinder the demand for products as well as the fulfillment of orders. Where your order fulfillment record is unsatisfactory, the number of customers and demand for products continuously decrease.

How to Forecast Demand Effectively?

Due to the flexible nature of demand, predicting future sales of a product is one of the most difficult tasks in economics. However, there are straightforward steps that businesses can follow to effectively predict future demands.

Step 1. Establish A Plan

Every company runs in its peculiar business environment and has different economic factors specific to it. Demand forecasting activities must be in sync with the peculiarities of your own company for them to be effective.

A plan needs to be made according to your business goals and objectives. The period you want to consider, as well as the product and customer category you wish to focus on need to be established beforehand.

Demand forecasting takes note of these factors to predict what your customers want, when they want it, and how much they want. It needs to fit your financial, marketing, operations, and logistics plans. It is important that these plans are established before proceeding with demand forecasting.

You get to know which demand forecasting technique is best in achieving your goals and make appropriate decisions concerning it when you establish a plan.

Step 2. Compile And Record Data

After deciding on your business goals and the appropriate type of demand forecasting technique to be used, you then need to compile your historical and external analytics data.

Demand forecasting does not work without data. Even startup companies without historical data still need to make macro-level economic analyses to have enough information to work with.

Historical sales data gives a great overview of how demand trends shape out to be in the future. Having knowledge of the usual time of demand spikes for a product, the number of stock-keeping units (SKUs) usually demanded, and the typical sales channel makes demand forecasting easier.

In stable business environments, internal historical data and trends are the only metrics required for accurate forecasts. General market data are, however, important key metrics for most companies and business types in very inconsistent business environments.

Step 3. Analyze Compiled Data

Demand forecasting does not end at just compiling internal and external economic data. Data still needs to be analyzed and converted to useful information.

Analyzing data can be done manually, using different economic equations and inferences. It can also be done with the use of automated software programs that are optimized for that exact purpose.

Your previous forecasts can be compared with the eventual demand and sales for that period under consideration to see areas for improvement. Variations between your prediction and actual occurrences help you measure the effects of miscalculations and opportunity costs suffered.

For instance, a graphical spike in demand shows a company that demand for a product increases during that period. From this, the company has an idea of what it needs for that period to avoid stock-out situations.

Of course, this spike could also be caused by other factors like the folding up of a competitor. Analyzing all the data compiled from sales history, internal operations, and the external general market environment helps you come up with the most appropriate forecast for the future.

Analyzing data helps you know how quickly products are selling and which items are slow-moving. It shows you how long your current inventory will take to run out, the profitability of each order, and where your customers from, among a whole lot of others.

Data analysis for demand forecasts is relatively much easier in stable economic environments where trends are expected to always be the same as in previous periods. No complex calculations are required unlike in business environments with inconsistent variables.

Step 4. Create Your Budgets Accordingly

After making the appropriate analyses, it is then time to come up with a demand forecast. Demand forecasts are expected to follow the various inferences made from the study of historical data and the general market metrics.

You adjust your budget and other allocations to fill loopholes in previous forecasts and also take care of estimated future needs.

Hopefully, these inferences are accurate and comprehensive enough for demand forecasts to also be accurate. Accurate demand forecasts help you reduce overall inventory costs, optimize marketing strategies and costs, and maintain the appropriate number of staff to meet demand.

Examples of Demand Forecasting

Different organizations have different business objectives and plans for their future. While some may decide to pursue stable growth, some may pursue aggressive growth, while some may choose to maintain their current economic positions.

Demand forecasting can be illustrated with the following examples.

An online store checks out its sales trends from last year’s winter to prepare adequate inventory levels for the upcoming season. Sales of seasonal products like waterproof boots, winter gloves, scarves, and winter coats are looked at. Analyses show that there was a great seasonal sale for them.

However, six months ago, a competing store opened close to it and, due to this, demand for products was expected to be skewed. However, at the same time, a lot of families continued to move into the neighborhood, and business growth remained at an average of 1% month-over-month since the competing store opened.

A plan to launch a few more promotional campaigns than last year is made and channels that have generated a good Return On Investment (ROI) are considered. Some new deals to position themselves as the go-to store are also proffered to customers.

Projected forecasts for demand can be put at a 5% increase in sales from last year and budgets can be made accurately.

A fast-growing direct-to-consumer (DTC) apparel brand starts off selling 10,000 units of inventory per month. Based on past sales data, upcoming promotional campaigns, and general market conditions in the industry, a plan to sell above 30,000 orders per month in the following year is then made.

Shortly after, a total of 30,000 inventory units were stocked up and at varying levels across their 5 different stock-keeping units (SKUs). The economic environment is considerably stable and order volume only fluctuates a bit based on their replenishment cycle. Inventory is also stocked at a rate of about every 90 days.

After reaching its 30,000 sales goal, a new plan to ship in another 50,000 units is then made based on historical sales data and the rate of demand is received.

With a long-term plan, the apparel brand plans to continuously grow at the same pace, so a longer projection of 75,000 units is made for the distant future. Other factors like the purchase of land, lease of a warehouse, or outsourcing of inventory fulfillment are also decided upon according to the projected demand.

Demand Forecasting FAQ

Demand forecasting helps the business make informed supply decisions that estimate the total sales and revenue for a future period.  A huge part of a business’s operational strategy is based on demand forecasting. Through it, they can predict inventory turnover, profit margins, cash flow, product availability, and capital expenditure.  Demand forecasting, for example, helps you to determine what products will have heavy traffic at a future date, like Christmas trees in the festive season.

Building a demand forecasting model relies on many factors including the context of the forecast, the viability of available historical data, the degree of accuracy desirable, the period to be forecast, the benefits of the forecast to the company.  Forecasting models can be generally differentiated into two groups based on whether they use qualitative or quantitative methods.   Models such as a time series model or an econometric model will use quantitative methods because they need large amounts of data to predict future demand trends.  On the other hand, qualitative research like the Delphi method or sales force composite will use human opinions where data is not available or applicable. Quantitative methods are more data-accurate but qualitative methods offer more flexibility. It can readily account for external factors like inflation and market competition, unlike the qualitative model.

Was This Article Helpful?

Anastasia belyh.

Anastasia has been a professional blogger and researcher since 2014. She loves to perform in-depth software reviews to help software buyers make informed decisions when choosing project management software, CRM tools, website builders, and everything around growing a startup business.

Anastasia worked in management consulting and tech startups, so she has lots of experience in helping professionals choosing the right business software.

• Sample Plans
• WHY UPMETRICS?

Upmetrics AI Assistant: Simplifying Business Planning through AI-Powered Insights. Learn How

• 400+ Sample Business Plans

Customers Success Stories

Business Plan Course

Strategic Canvas Templates

E-books, Guides & More

Business consultants

Entrepreneurs and Small Business

Accelerators and Incubators

Educators & Business Schools

Students & Scholars

AI Business Plan Generator

Financial Forecasting

AI Assistance

Ai pitch deck generator

Stratrgic Planning

See How Upmetrics Works  →

Small Business Tools

Entrepreneurs & Small Business

Accelerators & Incubators

Business Consultants & Advisors

Strategic Planning

7 Sales Forecasting Methods Explained with Examples

Free Sales Forecast Templates

Rudri Mehta

• December 13, 2023

The sales team spends 2.5 hours each week of their selling time on estimations and predictions. However, they can typically achieve less than 75% accuracy with an effective sales forecasting technique.

Forecasting sales is an important business task. A business leader needs accurate sales predictions to enable business leaders to make better decisions relating to setting targets, hiring, cash flow , and budgets .

Meanwhile, inaccurate sales forecasts for sales managers bring uncertainty that makes timely detection of problems in the sales funnel impossible.

This article discusses particular methods, examples, and pointers to create a viable sales forecast.

What is Sales Forecasting?

Sales forecasting is estimating the volume of sales for your company over a given period. An accurate sales forecast manages cash flow and allocates resources for future growth.

Sales projections typically use historical sales data, industry-wide comparisons, and current economic trends. Accurate sales forecasting depends on two factors: having the appropriate data and making the correct inferences. It is much easier to make a sales prediction when you have data.

Sales Forecasting Methods

Most organizations simultaneously employ sales forecasting strategies to obtain more projections. It can provide you with both the best-case and worst-case scenarios.

Length of Sales Cycle Forecasting

The forecasting approach for the sales cycle length uses data on the time it takes a prospective customer to convert into a paying customer.

This form of forecasting is objective because it does not rely on the emotions of your sales staff. It is ideal for businesses to track when new customers enter their sales pipeline.

“The most important thing is to forecast where customers are moving, and be in front of them.” – Philip Kotler, an American Author

Lead-Driven Forecasting

This algorithm analyzes previous sales data from each lead source to predict the future. You’ll need the following measurements: Leads per month for the preceding month. The average sales price varies depending on the source. Divide the total number of leads required in a given period by the average lead value.

The average sales cycle may vary depending on the lead source. Other business efforts may pact your conversion rates. Modify marketing plans in response to new information or trends. It syncs them to verify your predicted lead volume and conversion rates are correct.

Opportunity Stage Forecasting

This model predicts the likelihood of an opportunity closing based on the prospect’s position in your sales process. In this technique, you anticipate future sales by multiplying the amount of each opportunity by the probability of that opportunity closing.

This method needs a CRM system that automatically assigns win probability for each stage, essential for an accurate forecast.

Intuitive Forecasting

The intuitive forecasting method depends on your faith in your prospects’ opinions. Your salesman is the ideal person to ask whether the sale will go through or not. If the sales representatives are optimistic, they may make exaggerated predictions, and there is no way to evaluate the statistics.

Test-Market Analysis Forecasting

The forecasting method of Test-Market Analysis allows you to roll out your product or service to a specific set of people depending on their demands. You can use the rollout findings to produce a more accurate future market projection.

Historical Forecasting

Historical forecasting does not account for dynamic market developments. For example, if your competitors executed a promotional campaign, you might see a drop in sales. Using this strategy, you anticipate the MRR, assuming a 10% annual growth rate.

Multivariable Analysis Forecasting

Multivariable analysis forecasting is a fantastic choice if you want the most accurate forecasting method. It considers elements from different sales forecasting methodologies, such as opportunity stage forecasting and individual rep performance.

Because it requires complex calculations, this strategy may be impractical for small enterprises.

To bed, the Sales Forecasting methods, check out the examples.

Importance of Sales Forecasting

• Sales forecasting is all about accessing how much time you have left in your budget to spend on new items and services.
• Accurate estimates impart market credibility to publicly traded corporations .
• When sales leaders rely on forecasts, privately held enterprises gain confidence in their operations.
• Sales forecasting identifies potential issues and allows you to avoid or mitigate them.
• You can research and discover that there aren’t enough leads created for the sales team to convert.
• Sales predictions can also assist in hiring and resource/inventory management decisions.
• Assume your sales estimate predicts an increase in demand.

Sales Forecasting Examples

Ex. 1) using current funnel.

Assume you have three open positions this month: One with a brief phone call with an expected value of $2,000. Another believes it is worth $3,000 as he received a thorough demo, while another had an offer with a $2,400 estimated value.

The following possibilities could be there: “Phone Call” marks a 30% likelihood of closure. “Demo” may close at a 40% possibility while “Offer” has a 70% likelihood of closing.

To get a total sales prediction, you need to multiply the probabilities by the predicted value of the contract and add them all up to get $ 3,480, as shown in the following example:

Ex. 2) Using Lead Scores and Multiple Variables

You can use a table to forecast your sales using lead scores and multiple variables. Use average opportunity sizes to calculate the anticipated value of any specific chance:

Divide your leads into three groups of varying qualities: A, B, and C. These variables impact the chance of a closing deal.

Assume that the organizations with 50 or fewer employees close at a little lower rate, whereas companies with employees more than that have more probabilities of closing the deal.

Ex. 3) Using Historical Data

Assume you had $300,000 revenue last month and that your sales revenue has risen at a rate of 12% per month over the previous year. Your monthly churn was approximately 1%.

Your projected revenue for the following month will be:

($300,000 * 1.12) – ($300,000 * .01) = $333,000

It is derived by multiplying the past month’s income by the projected growth, and from the resultant amount, you need to deduct the churn.

Factors Influencing Sales Forecasting

• Economic conditions affect every firm and market. When the economy is in a slump, people/businesses lose money and are less likely to buy, whereas people are more likely to invest and buy when the economy is booming.
• Policy changes or implementing new laws/regulations can benefit or hinder your firm. You must consider these when forecasting your sales for the coming month.
• Changes in your product might have a significant impact on your sales estimate.
• Factors such as new technology advancements , design, competitors running promotional offers, or new businesses entering the fray might modify and affect the industry’s market share – which will factor into your sales estimates.

4 Tips That Will Help You Forecast Your Sales Effectively

Improving the accuracy and efficiency of your sales projections and forecast technique is dependent on several things, including good organizational coordination, automation, reliable data, and an analytics-based process.

1. Review Historical Data and Analyze Future Trends

To forecast your sales, you will need to understand the key details about similar products or services you are selling. You will also need to be careful about future trends to prepare from now itself.

The product you are selling has a raw material component that may lack in the future; you will need to have a backup plan.

2. Select Sales Forecasting Method

You must select the method that best explains your product or service to maximize your sales prediction. While predicting sales may look easy, selecting methods is more complex.

3. Understand Your Product or Service

If you are selling products or services of different categories, you need to identify them to predict their numbers better. If you include a product you no longer sell, your sales prediction may lead to incorrect results.

4. Multiply Sales Price and Quantities

Your sales price is fixed, and pre-determined. Hence, you need to estimate the number of units you will sell throughout the year. The prediction of the sales figures and their multiplication with the sales price will give you the sales prediction.

Final Words

A Sales forecaster must combine approaches with the managers’ knowledge and experience. The need is not for improved forecasting methodologies but for better utilization of the available tools.

While applying any forecasting technique takes patience, at Upmetrics , we help you optimize your sales forecasting process. Request your free demo.

Build your Business Plan Faster

with step-by-step Guidance & AI Assistance.

About the Author

Rudri is a passionate financial content writer and a Chartered Accountant by profession. She enjoys sharing knowledge through her writing skills in finance, investments, banking, and taxation while also exploring graphic designing for her own content.

Related Articles

How to Prepare a Financial Plan for Startup Business (w/ example)

Prepare Compelling Financial Projections for Startups

Budgeting Vs Forecasting Key Differences to Know

Reach your goals with accurate planning.

No Risk – Cancel at Any Time – 15 Day Money Back Guarantee

Popular Templates

No internet connection.

All search filters on the page have been cleared., your search has been saved..

• All content
• Dictionaries
• Encyclopedias
• Expert Insights
• Foundations
• How-to Guides
• Journal Articles
• Little Blue Books
• Little Green Books
• Project Planner
• Tools Directory
• Sign in to my profile My Profile

• Sign in Signed in
• My profile My Profile

Qualitative Forecasting Models

• By: Avinash Bagul Edited by: Rajni Kant Rajhans
• Product: Sage Research Methods: Business
• Publisher: SAGE Publications Ltd
• Publication year: 2023
• Online pub date: March 21, 2023
• Discipline: Business and Management
• Methods: Forecasting , Statistical modelling , Quantitative data collection
• DOI: https:// doi. org/10.4135/9781529669244
• Keywords: business planning , consumer behavior , expert opinion , intention , managers , opinions , organizations Show all Show less
• Academic Level: Postgraduate Online ISBN: 9781529669244 More information Less information

This guide introduces the readers to the concept of forecasting, which is the basis for business planning activities. Forecasting involves the prediction of outcomes, model estimates, analyzing data, and is based on expert opinion. General applications of forecasting are discussed. Forecasting is classified based on time horizon and its impact on various organizational decisions is assessed.

The importance of forecasting and the role of managers in forecasting is emphasized using suitable examples. Classification of forecasting methods into quantitative and qualitative methods is done along with a brief overview of quantitative methods. This is followed by a detailed discussion on qualitative forecasting methods, which includes expert opinions, the Delphi method, scenario analysis, case study method, brainstorming, consumer opinion, and intentions. At the end of the guide, a stepwise approach is suggested for qualitative forecasting methods.

Learning Outcomes

By the end of this guide, readers should be able to:

• Define the concept of forecasting and discuss its general applications
• Describe the importance of forecasting in business decision-making
• Analyse qualitative methods of forecasting
• Discuss the stepwise approach for qualitative forecasting

Introduction to Forecasting

Organizations generally operate in an uncertain business environment. Therefore, managers must systematically plan business activities to attain organizational objectives. For the planning of business activities, organizations often rely on forecasting. Hegre et al. (2017) defined forecasting as “prediction about unrealized outcomes, given model estimates which are realized by analyzing past data and expert opinion.” Forecasting can be undertaken by using either quantitative or qualitative methods. Quantitative methods make use of numeric data whereas, qualitative methods rely on the opinion, knowledge, and expertise of the managers. Some of the common examples of forecasting include economic forecasts made by government agencies, forecasts on population growth, forecasts on technological changes, etc. The economic forecast consists of trends in gross domestic product (GDP), employment rate, interest rate, and foreign exchange rate. Banks can use this data to forecast demand for their loan product offerings. A forecast released by the government on population growth acts as a basis for planning activities on infrastructure development. Based on the technological forecast, telecom and software companies can make changes in their product offerings.

With the information on anticipated demand for the products, an organization can plan its business operations. The production department uses forecasts to schedule production activities, procure materials from suppliers, plan inventory, and schedule dispatches. The marketing department uses sales forecasts to set sales goals, allocate salesforce, and plan promotional activities. Labor scheduling, plant capacity planning, and maintenance schedules are some of the other activities that are based on forecasting.

The forecast is always made about a specific time horizon. Generally, the forecast made for a period of six months to two years is referred to as a short-range forecast and it impacts the operational decisions of an organization. Medium range forecast extends to a period of two to five years and impacts tactical decisions like structure and size of the workforce, marketing, and sales strategy. Long-range forecast extends to more than a five-years and influences strategic decisions like capacity expansion, entry into new markets, facility location, and layout.

The information that forms the basis of forecasting is the data that is often dispersed throughout the organization. This data needs to be collected and analyzed to arrive at the forecast. Although organizational data acts as the basis of forecasting, there might exist instances whereby organizations rely on the knowledge and expertise of various stakeholders in arriving at a forecast. For example, in the case of introduction of the new products, historical data may not be available and organizations can use qualitative methods for forecasting by utilizing the expertise of the managers.

Section Summary

• Forecasting impacts the operational decisions made by an organization.
• Forecasting methods are divided into two groups i.e. quantitative methods and qualitative methods.
• Quantitative methods make use of numeric data whereas qualitative methods rely on expert opinion.
• The types of forecasts made by an organization are based on the time horizon and many organizational decisions can be taken considering the forecast.

Importance of Forecasting

Informed decisions can be taken by an organization using forecasting data. This can help reduce risk in business decision-making. Forecasting can aid in setting organizational goals and aid in developing strategies to achieve them. The role of managers is crucial in developing forecasts. Based on knowledge and experience, managers develop qualitative forecasts by analyzing past operations. Such a forecast can identify potential growth areas for the organization. It can also help in knowing how an organization might perform in near future.

With clarity on future trends, businesses can allocate additional budgets to new product offerings. Accounting activities such as cost estimation, funds management, product profitability, etc. can be effectively done in the light of the forecasting information. If the forecasting suggests an increasing trend in demand, then funds can be arranged for capacity expansion. If the existing capacity is not sufficient to satisfy demand, then the decision on the level of outsourcing can be taken. Accurate forecasting helps organizations project profitable product lines and estimate revenue for each product.

• Forecasting is important in the accounting and operations functions of an organization.
• The opinion of experts is important in forecasting.
• Forecasting plays a role in directing organizational performance by influencing decision-making.

Qualitative Forecasting Methods

Forecasting methods are broadly divided into two groups, quantitative (statistical) and qualitative (judgemental) methods ( Caniato et al., 2011 ). Quantitative methods are based on historical data and can be useful when demand is relatively stable. The data sources for this method include sales data, production data, product data of the competitors, and data from industry associations. These methods are further subdivided into two groups viz. time series method and the regression method. The time series method includes simple moving average, weighted moving average, and exponential smoothing method. The regression method tries to develop a forecast by using past data. The existence of a linear relationship between the variables is the basic assumption in regression analysis.

In some instances, like the erection of a new oil refinery or the setting up of a power project, organizations may not have enough past data. This restricts the use of quantitative methods and therefore, qualitative methods are employed for forecasting. These methods make use of subjective inputs from different stakeholders of the organization. Changes in the macroeconomic environment such as political changes, fluctuations in the exchange rate, and a surge of digital technologies may advocate the use of these methods. In the post-Covid scenario, there is a surge in platform-based businesses. For such businesses, past data is seldom available and therefore forecasts can be done using expert opinion. If there is a major disturbance expected in the economy, such as war or a natural calamity, then qualitative methods are advisable. For example, the housing industry worldwide has been affected by the surge in steel prices in the last few years, while experts in the industry had already warned about this increase.

The advantages of qualitative methods are that these methods are inexpensive and do not require a high level of statistical knowledge. However, limitations of these methods are the subjectivity of the judges, underestimation of forecasts by the experts, and changes in human opinions with time. In these methods, experts try to identify and analyze the relationship between their knowledge of past operations and potential future operations. Qualitative forecasting methods include executive opinions, the Delphi method, scenario analysis, case study method, brainstorming, consumer opinion, and intentions. These methods are explained as follows.

Executive Opinions

In the executive opinions method, all line managers sit together, and based on collective opinion, a forecast is made. The basic principle underlying this method is that the group can provide a more accurate forecast compared to the individuals. This method is used along with quantitative methods such as trend analysis. Initially, a forecast is made using quantitative methods. The forecast values are then modified by a group of managers from diverse areas. The knowledge and expertise of managers are used to arrive at the final forecast value. Limitation of the method includes the formation of collective opinion leading to group pressure. This may suppress logical criticism from a few managers. Also, one department manager may dominate the opinion and can influence the forecast.

Delphi Method

An important limitation of the executive opinion method is a dominance of one manager. This may create bias in forecasting. Also, there will always be a higher weightage given to senior-level managers compared to lower-level managers. For eliminating this bias, an iterative process called the Delphi method is advocated. The method was developed by Rand corporation in 1950 for the U.S. Air force funded project. In this method, an effort is made to establish consensus on the forecast by the panel of experts, Modrak and Bosun (2014) . Key considerations in this method are the selection of the panelists, the number of panelists, the number of rounds, the anonymity of feedback, and forecasting analysis, Ameyaw et al., (2016) . In this method, an anonymous survey is conducted with the help of a detailed questionnaire. The respondents for the survey are the senior managers who respond to the set questionnaire based on their knowledge and expertise. Generally, the responses received are kept confidential to reduce bias. Impartiality in judgment is ensured as respondents fill out the questionnaire independently. Detailed steps to be followed in the method are given in Figure 1 .

From left to right the sequence of interconnected 6 steps depicted is as follows.

Constitute group of experts (step - I)

Prepare a questionnaire (Step - II)

Circulate questionnaire in the group (Step - III)

Recirculate questionnaire in the group (Step - V)

Present the result (Step - VI)

Figure 1. Steps in forecasting using the Delphi method.

The first step in the Delphi method is to constitute a group of experts who respond to the detailed questionnaire on forecasting. These experts must be well-versed in the working of the Delphi method. The second step constitutes the preparation of a detailed questionnaire. The questionnaire must be concise, unambiguous, and focused on the specific area of forecasting. Once the questionnaire is prepared, it is circulated among the group of experts. After receipt of the responses, results are compiled. In step five, based on the results obtained, the revised questionnaire is prepared and feedback is given to the respondents considering the group consensus. The revised questionnaire is recirculated among the experts, and the forecast is revised based on the analysis of final responses. The feedback loop continues until the final forecast is presented.

The key feature of the Delphi method is anonymity, as it allows experts to express their opinion freely without considering peer opinions, Hanke and Dean (2014) . The method is iterative in nature and provides flexibility to the experts to revise their opinion based on the feedback received. Personal influences are minimized as the final forecast is based on group opinion. The method is flexible in nature and can be applied in diverse situations.

Scenario Analysis

Scenario analysis is the forecasting technique in which several possible scenarios are developed by the managers and the expected outcome is assessed for each scenario. Generally, three types of scenarios are developed: optimistic, pessimistic, and realistic. An optimistic scenario is one in which the business environment is in favor of the organization, whereas in a pessimistic scenario, the business environment is against the organization. A realistic scenario is mid-way between an optimistic and pessimistic scenario. Under each of these scenarios, the expected outcome of the business is assessed. The goal is to select the best course of action for the organization. Such an analysis tries to identify the opportunities and threats existing in the external environment and helps the organization change its strategy. The choice of the scenarios depends on human judgment. The four-step approach for scenario analysis is given in Figure 2 below.

From left to right the sequences of interconnected steps depicted are as follows.

• Define the time frame and scope of analysis (Step-I)
• Identify key factors and trends that may impact forecasting and create different scenario (Step – II)
• Identify and focus on key scenarios (Step – III)
• Measure impact of each scenario on the expected outcome (step – IV).

Figure 2. Forecasting using scenario analysis.

In the first step, the time frame for forecasting is defined along with its scope. Based on the defined scope, key factors that may impact the forecast are defined and different scenarios are created. Out of the number of scenarios developed, key scenarios are identified in step three for further analysis. In the last step, the expected outcome for each scenario is calculated. This method is useful when an organization works under risk and uncertainty and when forecasting is to be made for a longer period. One of the limitations of the method is that there exists a large number of factors under which an organization operates and all these factors are difficult to quantify. The method is especially useful in improving the quality of planning by considering risk and uncertainty.

Case Study Method

A case study is a detailed description of a particular business problem faced by an organization. For analyzing the case, a person needs to act as a decision-maker for the organization. After a detailed analysis of the problem from the perspective of the organization under consideration, recommendations are provided on the given problem. Based on individual knowledge, experience, and creativity, alternate viable solutions are obtained. An important feature of this methodology is its holistic character; i.e., an aspiration for getting a complete solution to the given problem. Case study analysis can be effectively used in business forecasting considering inputs received from different experts by analyzing the case.

Brainstorming

Brainstorming is the group approach in which a group is exposed to a business problem and its spontaneous solutions are obtained. Discussion in the group happens based on the given ‘problem statement’. The group members are chosen from different areas of the organization. This technique tries to find unusual solutions to business problems by encouraging the creativity of the group. The degree of group creativity significantly impacts the application of this method. The method can be successfully applied to forecast demand for new products. For example, if an educational institution that provides offline programs is interested in launching online programs, it may estimate demand for the programs by conducting brainstorming sessions with students, faculty members, and staff.

Consumer Opinion

Understanding consumer opinion on product offerings is extremely important as organizations produce products for the ultimate use of the consumers. The consumers form an image of the products based on their opinion and attitude. Therefore, it is necessary to understand consumer attitudes through surveys. These surveys can highlight important qualitative dimensions of consumer behavior and managers can use this information to predict demand for the product. For example, a survey on edible oil consumers may reveal that they do not repeat their purchases because of the inferior quality packaging material used. stated that the marketing and sales department plays an important role in understanding consumer behavior and are the most frequent contributors to forecasting in American businesses.

In the case of new products or products being introduced in new markets, marketers may not be sure of the demand for the products. In such a scenario, marketers can ask consumers whether they intend to purchase the product or not. These responses often act as inputs to forecast demand for the products. Morwitz (2001) developed nine principles of use of intentions to predict consumer behavior. These principles reveal that intention yields more accurate consumer behavior when consumers are engaged in similar kinds of behavior in the past.

• Forecasting methods include quantitative and qualitative methods.
• Quantitative methods of forecasting include time series and regression method.
• A variety of qualitative methods of forecasting are available.
• Qualitative methods of forecasting have the advantages that these methods are inexpensive and do not require a high level of statistical knowledge and the limitations are subjectivity of the judges, underestimation of forecasts by the experts, and changes in human opinions with time.

Steps in Qualitative Forecasting

With the understanding of the different qualitative forecasting methods, Figure 3 provides general steps followed in the implementation of these methods as derived from Frechtling (2012) .

Step - I: Problem formulation and selection of forecasting method

Step - II: Selection of the respondents

Step - III: Preparation of questionnaire

Step - IV: Responses to the questionnaire

Step - V: Obtaining forecast

Figure 3. Steps in qualitative forecasting.

Problem formulation and selection of forecasting method

The first step in qualitative forecasting is problem formulation. The time frame and the product under consideration are the two important considerations in this step. After formulation of the problem, an appropriate method of forecasting needs to be decided. For example, with newer products, brainstorming is an appropriate method, and for launching an existing product in a new market, the consumer opinion method would be appropriate.

Selection of the respondents

In this step, respondents are selected based on their knowledge and prior experience in the area for which forecasting is made. In the case of the Delphi method and scenario analysis, the respondents selected are the experts in the field whereas, for consumer opinion and intentions, respondents are the actual consumers of the products.

Preparation of questionnaire

Forecasting is a complex process involving multiple parties, and multiple data sources, and makes use of multiple methods. These complexities often lead to ambiguity among practitioners. Therefore, a detailed questionnaire must be prepared which should be unambiguous and free from jargon. The nature of the questionnaire depends on the selection of the qualitative forecasting method.

Responses to the questionnaire

Once the questionnaire is prepared, respondents need to be briefed about the objective of the process. This facilitates the extraction of the right information from the respondents. The selection of the number of respondents depends on the type of forecasting method employed. For example, for scenario analysis and the Delphi method, the number of respondents may be very limited but in the case of the consumer opinion and intentions method number of respondents would be large.

Obtaining a forecast

The last step is to obtain a forecast by analyzing the responses. Forecasting data may be collected from different sources in different formats. This data needs to be cleaned for further analysis. Data cleaning is the process of identifying incomplete, inaccurate, and irrelevant part of the data and modifying it for further analysis. For example, in a consumer survey, some of the respondents may not fill questionnaire completely, provide incorrect responses or there might be the selection of wrong respondents. Such data needs to be refined and then analyzed further to obtain the final forecast. In some methods like the Delphi method, the forecast obtained is again passed on to the respondents to revise the forecast.

All the qualitative methods discussed above are confined to the major stakeholders of the organization. However, business always works in a dynamic external environment, and the help of external consultants may also be required in making the forecast. An integrated approach considering quantitative and qualitative methods can provide a better forecast for the organization. Based on the case studies for the cement industry, Blattberg and Hoch (2010) stated that such an integrated approach outperforms the individual approach. Although both approaches have their relative advantages and limitations, usage of any of the approaches depends upon the quantity and quality of the data available to the organization.

• A stepwise approach for qualitative methods of forecasting consists of problem formulation, selection of the forecasting method, selection of the respondents, preparation of the questionnaire, responses to the questionnaire, and obtaining the final forecast.
• Understanding of external environment through consultant opinion is also essential in forecasting.
• It is important to use an integrated approach to forecasting.

The objective of this guide is to make the readers acquainted with the concept of forecasting with special emphasis on qualitative methods. Initially, a brief introduction to forecasting is done along with its different application areas. This acquaints the readers with the concept of forecasting which is a basic planning tool for organizations. The importance of forecasting is emphasized for the long-run survival of the organizations. Different methods of qualitative forecasting are discussed along with their specific application areas. A systematic stepwise approach to qualitative forecasting is illustrated.

By going through the guide, the readers will get a fair idea about the forecasting process. An elaborate discussion has been done on qualitative forecasting methods which can help in developing a robust forecasting process. With a better understating of the process, readers can actively contribute to the forecasting process in the organization they work with, to enhance organizational profitability.

Multiple-Choice Quiz Questions

1. Who are the respondents in the Delphi method of forecasting?

Correct Answer

Feedback: Well done, correct answer

Incorrect Answer

Feedback: This is not the correct answer. The correct answer is A.

2. Which of the following forecasting method is suitable for understanding consumer opinion about the existing products in the new market?

Feedback: This is not the correct answer. The correct answer is C.

3. Which of the following is a qualitative method of forecasting?

Feedback: This is not the correct answer. The correct answer is B.

4. The qualitative method of forecasting specifically focusing on the creativity of the respondents is known as ______.

5. Which of the following qualitative method of forecasting is useful under the condition of risk and uncertainty?

Further Reading

Web resources, sign in to access this content, get a 30 day free trial, more like this, sage recommends.

We found other relevant content for you on other Sage platforms.

Have you created a personal profile? Login or create a profile so that you can save clips, playlists and searches

• Sign in/register

Navigating away from this page will delete your results

Please save your results to "My Self-Assessments" in your profile before navigating away from this page.

Sign in to my profile

Sign up for a free trial and experience all Sage Learning Resources have to offer.

You must have a valid academic email address to sign up.

Get off-campus access

• View or download all content my institution has access to.

Sign up for a free trial and experience all Sage Research Methods has to offer.

• view my profile
• view my lists