Top 10 Manufacturing Analytics Use Cases in 2024

case study big data analytics in manufacturing

IDC estimates that the global big data analytics market revenue would’ve reached ~$274B by 2022. This would have made manufacturing as one of the top 3 industries with largest analytics growth.

Manufacturing analytics is one of the critical steps for manufacturing digital transformation required for Industry 4.0 , which aims to:

  • Automate traditional manufacturing processes
  • Reduce costs
  • Improve efficiency

What is manufacturing analytics?

Manufacturing analytics is the practice of capturing, cleansing, and analyzing machine data in order to predict their future use, prevent failures, forecast maintenance requirements, and identify areas for improvement. Manufacturing data includes all structured and unstructured information collected manually or by using software from machines and humans during every stage of production until a product is launched to the market.

Understanding Big Data Analytics for Manufacturing Processes

What are the use cases of manufacturing analytics?

Manufacturing processes produce a large volume of data from:

  • Machines: robotics, sensors, actuators, IoT devices, etc.
  • Operators: ERP, sales, logistics, etc.

This data can be collected and analytics can be applied to it for:

Supply chain

1. demand forecasting.

Demand forecasting relies heavily on historical data about supply levels, material costs, purchase trends, and customer behavior. Manufacturers can leverage analytics to:

  • define the types of products to be manufactured in a certain period
  • define out of stock products
  • calculate the number of products to be manufactured
  • forecast sales opportunities

2. Inventory management

Forecasting demands enables manufacturers to manage their inventory, purchase materials, and optimize storage capacities in a data-driven manner. Analytics also provides insights about:

  • sales to inventory ratio which represents the average inventory over the net sales
  • days in inventory which is the number of days a manufacturer holds their product before selling it)
  • gross margin return on inventory (GMROI) which indicates how much gross margin a manufacturer gets back for each dollar invested in inventory. 

Explore inventory management in more details.

3. Order management

Manufacturers can leverage predictive analytics to optimize the order management workflow by identifying products in demand, calculating the time required to build and ship every product, and defining the inventory needed to meet the demand for the finished product.

Explore order management in more details.

4. Maintenance optimization

Data collected from different manufacturing machines, tools, and devices, as well as data about operations and which machines they require, can be analyzed in order to:

  • Predict when a machine will require maintenance based on time it’s been used and operations used in.
  • Detect anomalies in operations which are caused by or will lead to machine failure.
  • Prevent down time by planning machine breaks, fixes, or replacements.

Explore predictive maintenance in more details.

5. Risk management

Implementing analytics enables manufacturers to manage risks in a data-driven manner, such that they can:

  • Determine recurring errors and prevent repetitive losses
  • Predict insurance needs
  • Monitor real-time machinery and operator work
  • Identify real-time fails and system anomalies
  • Plan risk management strategies

6. Price optimization

Leveraging analytics can help manufacturers understand the real price of a product based on the prices of materials, cost of operations, machines, and tools used or purchased for manufacturing. Additionally, manufacturers can leverage data about competitors, market trends, consumer behavior, and purchase history to optimize prices accordingly. Analytics can also help set dynamic prices which are based on demand, supply, competition price, and subsidiary product prices.

7. Automation and robotics

Analytics can provide an overall view of a manufacturing process, operation costs, as well as the number of operators and hours spent on a product. Large manufacturing firms can leverage these analyses to uncover automation or robotization opportunities which can reduce the time and cost of launching certain products

8. Transportation allocation

Manufacturers can leverage analytics on:

  • Historical data : For predicting transportation time and vehicle requirements to deliver products to businesses or consumers.
  • Real time data : For analyzing the impact of unplanned transportation events such as labor strikes or road works.

Product development

9. product progress measurement.

Based on historical data about the same or similar products, materials, machines, and tools used, as well as allocated employees for production, analytics can provide an estimation about the production process, when the product will be launched, which errors or pitfalls may be faced, and create a roadmap for the following procedures.

10. End user experience estimation

Product development teams can leverage analytics on product features, consumer behavior, and comments on online platforms, as well as competitor products, to estimate why end users buy certain products, when to launch similar products, and which features require optimization.

What other technologies are used in manufacturing?

case study big data analytics in manufacturing

Some of the technologies leveraged today by manufacturers include:

Robotic process automation (RPA)

RPA is a type of software capable of replicating human interactions with computers in order to automate repetitive processes. Manufacturers can leverage RPA for supply chain management and stock optimization.

To explore use cases, feel free to read our article about the benefits and top 8 use cases of RPA in manufacturing .

AI has numerous applications in manufacturing including:

  • Digital twins and digital twin of an organization
  • Augmented reality
  • Demand forecasting
  • Generative design
  • Quality assurance
  • Process optimization

To explore AI use cases in manufacturing, read our in-depth article top 12 use cases and applications of AI in manufacturing .

If you believe your business will benefit from manufacturing technologies, feel free to check our data-driven lists of vendors for:

  • Manufacturing Analytics Software
  • Manufacturing API
  • IoT Analytics Platform
  • RPA Software
  • Web Crawler

And you can contact us to guide you through the process

case study big data analytics in manufacturing

Cem has been the principal analyst at AIMultiple since 2017. AIMultiple informs hundreds of thousands of businesses (as per similarWeb) including 60% of Fortune 500 every month. Cem's work has been cited by leading global publications including Business Insider , Forbes, Washington Post , global firms like Deloitte , HPE, NGOs like World Economic Forum and supranational organizations like European Commission . You can see more reputable companies and media that referenced AIMultiple. Throughout his career, Cem served as a tech consultant, tech buyer and tech entrepreneur. He advised businesses on their enterprise software, automation, cloud, AI / ML and other technology related decisions at McKinsey & Company and Altman Solon for more than a decade. He also published a McKinsey report on digitalization. He led technology strategy and procurement of a telco while reporting to the CEO. He has also led commercial growth of deep tech company Hypatos that reached a 7 digit annual recurring revenue and a 9 digit valuation from 0 within 2 years. Cem's work in Hypatos was covered by leading technology publications like TechCrunch and Business Insider . Cem regularly speaks at international technology conferences. He graduated from Bogazici University as a computer engineer and holds an MBA from Columbia Business School.

To stay up-to-date on B2B tech & accelerate your enterprise:

Next to Read

Top 6 digital twins use cases for manufacturing in 2024, 14 case studies of manufacturing analytics in 2024, complex event processing in 2024: use cases & top tools.

Your email address will not be published. All fields are required.

Related research

What is Analytics? How is it Evolving in 2024?

What is Analytics? How is it Evolving in 2024?

Healthcare Analytics: Importance & Market Landscape in 2024

Healthcare Analytics: Importance & Market Landscape in 2024

Book cover

Technologies and Applications for Big Data Value pp 321–344 Cite as

Big Data Analytics in the Manufacturing Sector: Guidelines and Lessons Learned Through the Centro Ricerche FIAT (CRF) Case

  • Andreas Alexopoulos 7 ,
  • Yolanda Becerra 8 ,
  • Omer Boehm 9 ,
  • George Bravos 10 ,
  • Vassilis Chatzigiannakis 10 ,
  • Cesare Cugnasco 8 ,
  • Giorgos Demetriou 11 ,
  • Iliada Eleftheriou 12 ,
  • Spiros Fotis 7 ,
  • Gianmarco Genchi 13 ,
  • Sotiris Ioannidis 14 , 15 ,
  • Dusan Jakovetic 16 ,
  • Leonidas Kallipolitis 7 ,
  • Vlatka Katusic 11 ,
  • Evangelia Kavakli 12 ,
  • Despina Kopanaki 15 ,
  • Christoforos Leventis 15 ,
  • Miquel Martínez 8 ,
  • Julien Mascolo 13 ,
  • Nemanja Milosevic 16 ,
  • Enric Pere Pages Montanera 17 ,
  • Gerald Ristow 18 ,
  • Hernan Ruiz-Ocampo 11 ,
  • Rizos Sakellariou 12 ,
  • Raül Sirvent 8 ,
  • Srdjan Skrbic 16 ,
  • Ilias Spais 7 ,
  • Giuseppe Danilo Spennacchio 13 ,
  • Dusan Stamenkovic 16 ,
  • Giorgos Vasiliadis 15 &
  • Michael Vinov 9  
  • Open Access
  • First Online: 29 April 2022

11k Accesses

2 Citations

Manufacturing processes are highly complex. Production lines have several robots and digital tools, generating massive amounts of data. Unstructured, noisy and incomplete data have to be collected, aggregated, pre-processed and transformed into structured messages of a common, unified format in order to be analysed not only for the monitoring of the processes but also for increasing their robustness and efficiency. This chapter describes the solution, best practices, lessons learned and guidelines for Big Data analytics in two manufacturing scenarios defined by CRF, within the I-BiDaaS project, namely ‘Production process of aluminium die-casting’, and ‘Maintenance and monitoring of production assets’. First, it reports on the retrieval of useful data from real processes taking into consideration the privacy policies of industrial data and on the definition of the corresponding technical and business KPIs. It then describes the solution in terms of architecture, data analytics and visualizations and assesses its impact with respect to the quality of the processes and products.

  • Self-service solution
  • Manufacturing
  • Die-casting
  • Maintenance and Monitoring
  • Advanced analytics and visualizations

Download chapter PDF

1 Introduction

The manufacturing industry transforms material or assembles components to produce finished goods that are ready to be sold in the marketplace. The organizational structure of manufacturing companies is very complex and involves many business and operative functions with different roles and responsibilities in order to guarantee efficiency at every level [ 1 ]. The fourth industrial revolution [ 2 , 3 ] has initiated many changes in the industrial value chain, transforming the shop floor, which is the production part of the manufacturing industries. Companies are introducing process equipment provided with several robots and digital tools. In this way, it is possible to set and control processes in an automated manner that speeds up production with a high level of accuracy [ 4 ]. Furthermore, large volumes of data are generated every day that may be collected and analysed for increasing process robustness and efficiency and building a technical cycle that reduces the consumption of energy and material. However, despite the potential benefits offered by the exploitation of Big Data, its usage is still at an early stage in many manufacturing companies [ 5 ].

Centro Ricerche FIAT (CRF) is one of the main private research centres in Italy and represents Fiat Chrysler Automobiles (FCA) in European and national collaborative research projects. In the context of the European Horizon 2020 I-BiDaaS project, Footnote 1 CRF identified two use cases, in which complex datasets are retrieved from real processes. By exploiting Big Data analytics in these two cases, CRF aims to improve the process and product quality in a much more agile way through the collaborative effort of self-organizing and cross-functional teams, reducing costs due to further processing and predicting faults and unnecessary actions. This requires solutions that will allow manufacturing experts to interact with Big Data [ 6 ] in order to understand how to easily utilize important information often hidden in raw data. In other words, the first best practice (1) Footnote 2 is the correlation between the value of Big Data technology and the skills of people involved in the data management process. The I-BiDaaS approach follows this best practice and develops a self-service [ 7 ] Big Data analytics platform that enables different CRF end-users to exploit Big Data in order to gain new insights assisting them to make the right decisions in a much more agile way.

The aim of this chapter is to demonstrate how advanced analytic tools can empower end-users [ 8 ] in the manufacturing domain (see Sect. 5 ) to create a tangible value from the process data that they are producing, and to identify a number of best practices, guidelines and lessons learned. For future reference, we list here the main best practices with the identified guidelines and lessons learned, while they will be discussed in detail throughout the chapter:

The correlation between the value of Big Data technology and the skills of people involved in the data management process with the involvement of different departments belonging to the same or different organizations in order to extract the value of all data collected from several sources and levels (breaking data silos).

The alignment of the Big Data requirements with the business needs and the definition of appropriate experiments with the identification of Big Data technologies most suitable for the specific identified business requirements.

The management of the type of data generated with the identification of the types of data useful for the analysis, their anonymization and generation of synthetic data in parallel with the process of data anonymization.

The development of a solution that satisfies Big Data requirements of specific use cases by mapping the identified functional and non-functional concerns into a concrete software architecture with the development of Advanced Visualization tools for showing high-value Big Data analytics solutions for domain experts and operators.

The remainder of this chapter is organized as follows. Section 2 describes the process followed for the identification of the Big Data requirements in the manufacturing sector and demonstrates how it was applied to elicit the requirements of the CRF use cases, which are imposed the design of the I-BiDaaS Big Data solution. Furthermore, CRF requirements guide the definition of the experiments for assessing the developed system, described in Sect. 3 . The architecture of the I-BiDaaS solution is described in Sect. 4 . Finally, Sect. 5 reports on the lessons learned, challenges and guidelines reflecting the experience of the I-BiDaaS project. Section 5 also provides the connection of the described work with the Big Data Value (BDV) reference model and its Strategic Research and Innovation Agenda (SRIA) [ 9 ]. Finally, Sect. 6 concludes the chapter.

2 Requirements for Big Data in the Manufacturing Sector

Alignment between business strategy and Big Data solutions is a critical factor for achieving value through Big Data [ 10 ]. Manufacturers must understand how the adoption of Big Data technologies [ 11 ] is related to their business objectives in order to identify the right datasets and increase the value of the analytics results. Therefore tailoring Big Data requirements to the business needs is the second best practice (2) reported in this chapter.

In more detail, the I-BiDaaS methodology for eliciting CRF requirements draws on work in the area of early Requirements Engineering (RE), which considers the interplay between business intentions and system functionality [ 12 , 13 ]. In particular, the requirements elicitation followed a (mostly) top-down approach whereby business goals reflecting the company’s vision were progressively refined in order to identify the user requirements of specific stakeholder groups (i.e. data providers, Big Data capability providers and data consumers). Their analysis resulted in the definition of system functional and non-functional requirements, which describe the behaviour that a Big Data system (or a system component) should expose in order to realize the intentions of its users. This process was facilitated by the use of appropriate questionnaires. In the cases that information on the requirements was available (either collected in the context of the project setup phase, or identified through a review of related literature [ 10 , 14 ]), this was used to partly pre-fill the questionnaires and minimize end-users’ effort. Evidently, users were asked to check pre-filled fields and ensure that documented information was valid and accurate.

Table 1 gives a summary of the CRF requirements. Although it provides only an excerpt of the elicited CRF requirements, it demonstrates the application of the I-BiDaaS way-of-working in the CRF use cases.

In more detail, the strategic CRF business goal (R1) was refined into a number of more operational business goals that need to be satisfied through Big Data analytics (R3). In addition, a number of relevant KPIs (R6) were defined that can be used to assess the proposed solution (see Sect. 3 ). Continuing, at the user requirements level, requirements were described in terms of the characteristics of different data sources that are planned to be used (requirements R7 and R8), the analytics capability of the proposed solution envisaged (R9) and the different interface requirements of the end-users that will consume the analytics results (R10–R12). Finally, analysis of the above user requirements resulted in the generation of the system requirements, both functional (R13) and non-functional (R14 and R15). Although described in a linear fashion, the above activities were carried out in an iterative manner, resulting in a stepwise refinement of the results being produced. The complete list of CRF requirements elicited is described in detail in [ 15 ].

Further to forming the baseline of the I-BiDaaS solution (see Sect. 4 ), these requirements also assist the definition of experiments as described in Sect. 3 .

3 Use Cases Description and Experiments’ Definition: Technical and Business KPIs

The aim of experimentation is to assist stakeholders’ acceptance of any new Big Data solution. The definition of appropriate experiments is thus another best practice (3) reported in this chapter. In particular, the definition of CRF experiments aims at evaluating and validating the I-BiDaaS solution and its implementation in the context of CRF use cases. It follows a goal-oriented approach, whereby the experiment’s goal(s) towards which the measurement will be performed are defined, then a number of questions are formed aiming to characterize the achievement of each goal and, finally, a set of Key Performance Indicators (KPIs) and associated metrics is associated with every question in order to answer it in a measurable way.

The definition of each experiment also involved the specification of the experiment’s workload in terms of the use case datasets and type of analysis envisaged, as well as the definition of the experimental subjects that will be involved in the experiment, as reported in the following Sects. 3.1 and 3.2 that discuss, respectively, the ‘Production process of aluminium die-casting’ and ‘Maintenance and monitoring of production assets’ use cases.

3.1 Production Process of Aluminium Die-Casting

The ‘Production process of aluminium die-casting’ use case generates complex datasets from the production process of the engine blocks. During the die-casting process [ 16 , 17 ], molten aluminium is injected into a die cavity, mounted in a machine, in which it solidifies quickly. In this case, we have a large number of interconnected process parameters that influence the flow behaviour of molten metal inside the die cavity, and, consequently, the productivity and the quality [ 18 , 19 , 20 ]. Henceforth, the fourth best practice (4) is to identify the type of data generated. Data collected from several sources can be disorganized and in different formats and data may not be exploited.

In this use case, the data provided for the analyses consist of a collection of casting process parameters, such as piston speed in the first and second phase, intensification pressures and others. In addition to the process data, CRF also provided a large dataset of thermal images of the engine block casting process, under a hypothesis that there is a correlation among process data, thermal data and the outcome of the process.

For the mentioned complexity of the process, it is important to not only carefully design parameters and temperatures but also to control them because they have a direct impact on the quality of the casting.

Analysis of the datasets aims to predict whether an engine block will be produced correctly during the casting process in order to avoid further processing and scraps, which would lead to financial savings for the manufacturers.

To test the efficiency of the I-BiDaaS solution in this context, an experiment has been defined, as shown in Table 2 . As seen in Table 2 , the Business KPI ‘Product/service quality’ identified during requirements elicitation (see Sect. 2 ) was further elaborated in order to define appropriate metrics (quality control levels related to good and defective products) and to map it to appropriate indicators at the I-BiDaaS solution level (execution time, data quality, cost).

For each KPI, a baseline value for evaluating the performance of the I-BiDaaS solution has also been defined. For example, an increase of 2–6% of the quality control level related to good products and a decrease of 1–4% and 0.05–2% of the two quality control levels related to defective products is sought in order to satisfy manufacturers’ requests in terms of product quality.

3.2 Maintenance and Monitoring of Production Assets

In this use case, data have been retrieved from sensors mounted on several machines (e.g. linear stages, robots, elevators) along the production line of vehicles. Many related works are conducted in this field concerning, e.g., sensor applications in tool condition monitoring in machining [ 21 ], predictive maintenance of industrial robots [ 22 ] and assessing the health of sensors using data historians [ 23 ].

We focused on welding lines in which robots are used to assemble vehicle components, and flexibility is required for the continual changes of the types of components and vehicles. A data server gathers sensor data, which is categorized into two different datasets, namely SCADA and MES. The SCADA dataset contains production, process and control parameters of daily vehicle production and is structured as in Table 3 .

There are over 100 sensors and each one is identified by a specific number (id). The other columns report on the value of the specific sensor, the unit of measurement and the timestamp.

The MES dataset contains specific data associated with the type of vehicle being produced and is structured as in Table 4 .

When OP020.Passo20 changes from 0 to 1, a new vehicle enters into the area provided with sensors and modello_op_020 indicates the model of the vehicle being processed.

Analysis of this data aims at predicting unnecessary actions and the improvement of the efficiency of manufacturing plants by reducing production losses. Once again, an experiment has been defined in order to test the efficiency of the I-BiDaaS solution in this context. The key points of the ‘Maintenance and monitoring of production assets’ experiment are shown in Table 5 . In particular, data was analysed to obtain thresholds for anomalous measurements for all sensors. The fifth best practice (5) is the building of a foundational database with the history of anomalies that may help end-users to plan maintenance through prevision of asset failures only when it is necessary.

As shown in Table 5 , the business KPIs reported during requirements elicitation were further elaborated to identify related metrics (Overall Equipment Effectiveness (OEE) [ 24 , 25 ] and maintenance costs [ 26 ]) and to map them on specific indicators at the Big Data solution level (execution time, data quality and cost).

For each KPI, a baseline value for evaluating the performance of the I-BiDaaS solution has been defined. For example, the prediction of unnecessary actions and the improvement of the efficiency should reduce production losses and achieve greater competitiveness of the company by an increase of 0.05% of the current Overall Equipment Effectiveness (OEE) and a decrease of 50% in maintenance costs.

4 I-BiDaaS Solutions for the Defined Use Cases

The final best practice (6) reported in the following sections relates to the development of a solution that satisfies Big Data requirements of specific use cases by mapping the identified functional and non-functional concerns into a concrete software architecture [ 27 ]. In particular, the general requirements reported in Sect. 2 were further clarified, taking into consideration the specific context of each use case (described in Sect. 3 ), resulting in customized solutions per use case described in Sects. 4.1 and 4.2 .

For both use cases, data gathered from the production lines are sent to CRF, where they are manipulated and masked. After the anonymization, data are sent to the I-BiDaaS Platform, hosted in a Virtual Machine. This represents a bridge between the I-BiDaaS infrastructure and CRF internal server, created by the I-BiDaaS technical partners. The same bridge is used to send the analytics results to the production plant end-users, as seen in Fig. 1 .

figure 1

Flow of data and results

4.1 Production Process of Aluminium Die-Casting

In this section, the architecture, data analytics, visualization and results for the ‘Production process of aluminium die-casting’ use case are described.

4.1.1 Architecture

Figure 2 shows the architecture of this use case, which consists of several well-defined components. The Universal Messaging component is used for communication with most of the other components. To start with describing the data flow for this use case, we first consider the dataset. Data is transferred from CRF’s internal server to the I-BiDaaS platform server. Therein, the data is pre-processed and cleaned—this step is important as the data needs to be prepared for model training and inference tasks. Then, the data is given to the Machine Learning algorithm from the I-BiDaaS pool of ML algorithms. In this use case, the model is a complex neural network implemented in PyTorch Footnote 3 and trained jointly from thermal images and sensor datasets. The Machine Learning component outputs two results: training metrics/results for visualization purposes—used in the Advanced Data Visualization component—and the trained model used for inference. Both these results are transferred through Universal Messaging. In the end, for inference purposes, the Model Serving (Inference) Service component is used. In the initial phases of development, before the real data is fully prepared (e.g. retrieved, anonymized, etc.), the architecture uses realistic synthetic data for initial components development. The use of synthetic data can make the development significantly more agile, but is utilized with care and under a quality assurance process. For example, a final trained ML model has to be delivered on real data. We refer to Sect. 4.1.5 for details on realistic synthetic data generation and quality assessment.

figure 2

Architecture of the ‘production process of aluminium die-casting’ use case

4.1.2 Data Analytics

In this section, we describe in more detail the data analytics solution that corresponds to the four respective modules in Fig. 2 (Data pre-processing, PyTorch neural network model, Trained model and Training results) and that analyses the thermal images and the sensors datasets.

Under the hypothesis that there is a correlation among sensor data, thermal data and the outcome of the process, a further task is to classify combined image and sensor data inputs to see whether the cast engine blocks are without any production faults. Formally, data analytics here corresponds to an M-ary supervised classification task [ 28 ]. As the dataset involves image classification, for this task we utilize Deep Convolutional Neural Networks [ 29 ].

We tried three approaches during this use-case analytics development regarding the input data: unmodified thermal images, grayscale thermal images and raw sensor data. For raw sensor data the thermal camera provides a matrix of values which is the same dimension as the image, which when normalized provides very similar (almost the same, depends on the normalization process) input to the grayscale image from the computing standpoint. While the grayscale image and the raw sensor data did have faster training times (one channel for convolutions versus three for thermal images) from our experiments the thermal images gave best accuracy/precision/recall metrics so we decided to keep using them. We suspect that this is the case because modern neural network architectures we are using (e.g. DenseNet [ 29 , 30 ]) are optimized to work with coloured images (e.g. ImageNet dataset [ 31 ]). The corresponding results are reported in Sect. 4.1.4 .

4.1.3 Visualizations

The approach to visualize the die-casting process results in real time involves the deployment of a number of constantly updated visualizations which offer a complete overview of the results. These include the values of monitored sensor variables and the final classification of the end products of the process.

We report here, as example, the Global Live Chart that allows end-users to timely visualize the trend of the main parameters (e.g. velocity, pressure, standard deviation, etc.) and to check the classification levels (Fig. 3 ).

figure 3

Real-time aggregated results

4.1.4 Results

The models described in Sect. 4.1.2 were trained on both the original and the newly balanced datasets. We favour the model trained on the balanced dataset as it learns to recognize faulty engine blocks much better than the model trained on the imbalanced dataset, even though the overall accuracy is lower—simply because we have less faultless engines. In Fig. 4 , we see the accuracies of both models on the training and testing datasets (standard 80/20 split). The orange (top) line is the model trained on the full dataset and the pink line is the model trained on the balanced dataset Footnote 4 [ 32 ].

figure 4

Training and testing accuracy for the two joint neural network models: when trained on full imbalanced data (orange line) and when trained on sub-sampled balanced data (pink line)

4.1.5 Synthetic Data Generation and Quality Assessment

An initial development of the use case solution was carried out with realistic synthetic data. In parallel with the process of data anonymization, making data structured, etc., it was useful to carry out a synthetic data generation for early development stages with particular caution when extracting insights from synthetic data.

The fabrication of synthetic data that exhibits similar characteristics and similar distribution as the real data is a challenging task. The IBM Test Data Fabrication technology (TDF) was used for that purpose. TDF requires constraint rules that model the relationships and dependencies between the data and leverages a Constraint Satisfaction Problems (CSP) solver to fabricate data that satisfies these constraints. The rules for the production of synthetic data were set by CRF with the help of IBM. The correlation between the real parameters and the synthesized parameters was further refined after reiteration of the data analysis.

For the initial evaluation of the synthetic data, we performed empirical and analytical validations. The empirical technique consisted of delivering these data to the expert production technicians, which were not able to indicate any difference with the actual production data, as there was no distinguishing factor for them. The second analytical technique was carried out by the CRF research team. They used the K-Means algorithm [ 33 ] as their desired technique. Further evaluation was carried out by IBM while striving to perform a qualitative generic evaluation process for the real data compared with the fabricated data. This evaluation was concerned with methods to judge whether the distributions of the fabricated data and the original data were comparable, what is commonly referred to in the literature as the general utility of the datasets. In addition to the general utility, IBM also considered the specific utility, i.e. the similarity between the synthetic data and the original data.

The propensity mean-squared-error (pMSE) [ 34 ] was used as a general measure of data utility to the specific case of synthetic data. Propensity scores represent probabilities of group memberships. If the propensity scores are well modelled, this general measure should capture relationships among the data that methods such as the empirical Cumulative Distribution Function (CDF) may miss.

The method is a classification problem where the desired result is poor classification (50% error rate), giving better utility for low values of the pMSE.

Randomly sampling 5000 data points from the real and synthetic datasets, and using a logistic regression to provide the probability for the label classification, we were able to show that the measured mean pMSE score for the ‘Production process of aluminium die-casting’ dataset is 0.218 with a standard deviation of 0.0017, as shown in Fig. 5 .

figure 5

Results for 100 random sampling taken from the real and the synthetic data (5K datapoints each) and the pMSE calculated using a logistic model

4.2 Maintenance and Monitoring of Production Assets

In this section, the architecture, data analytics, visualization and results for the ‘Maintenance and monitoring of production assets’ use case are described.

4.2.1 Architecture

Figure 6 shows the architecture, which consists of several well-defined components. The Universal Messaging component is used for communication in most of the components. To start to describe the data flow, we start with the dataset. Data are sent from CRF to the I-BiDaaS platform. There, the data is pre-processed and prepared for model training with an outlier detection model. The outlier detection model outputs two results: training results for visualization purposes—used in the Advanced Data Visualization component, and the trained model used for inference. Training results are transferred through Universal Messaging. In the end, for inference purposes, the Model Inference Serving component is used. It is also important to say that all the components use containerized (i.e. Docker Footnote 5 ) backbone from the Storage and Container Orchestration Service. Data is visualized and the jobs are scheduled through the I-BiDaaS User Interface component.

figure 6

Architecture of the ‘maintenance and monitoring of production assets’ use case

4.2.2 Data Analytics

Data, described in Sect. 3 , has been transformed into separate time series—one per sensor so that each sensor can be monitored separately. Since the measurements were not labelled (anomalous/non-anomalous), outlier detection algorithms arose as natural candidates for this use case [ 35 ]. We constructed an outlier detection model for each of the time series. While more advanced algorithms can be used, we adopted a simple, easy-to-implement and computationally cheap, yet here effective, solution based on the Inter-Quartile Range (IQR) test. Results of these models could be used for suggesting if a measurement is an outlier and for discovering the pairs of sensors that have anomalous measurements at similar timestamps. Preparation of these models was done using Python, and it consisted of the following steps:

For each sensor, obtain thresholds for anomalous measurements using a modified interquartile range (IQR) test. Three different variants of IQR-like tests were performed:

( Q 1 ,  Q 3 ) ∈ {(5th,  95th), (10th,  90th), (25th,  75th)} where Q 1 and Q 3 are the corresponding percentiles.

With obtained thresholds, filter the time series such that only anomalous measurements were kept, as shown in Fig. 8 .

Calculate the Dynamic Time Warping (DTW) [ 36 ] distance between outlier time series.

Rescale distances to [0, 1].

Group pairs of sensors by the distance into groups:

[0, 0.1), [0.1, 0.2)…[0.9, 1].

Time series with anomalous measurements obtained in step 2 enabled us to see the outlier trends for each sensor and to compare their behaviour. Comparison of anomalous trends was made using steps 3, 4 and 5. If the distance obtained in step 5 is small, it means that two sensors output anomalous measurements in a similar fashion. Therefore, if one of them fails, then the other sensor in the pair should also be inspected. We present the distribution of sensors’ similarity in Fig. 9 .

4.2.3 Visualizations

Data stemming from the aforementioned analysis are presented using a multi-step approach that allows operators drill down to sensory data and detected anomalies in an intuitive and easy-to-use way. Starting from a given month, operators then select the category of sensors they wish to see and immediately have an overview of the ones having anomalies detected, as shown in Fig. 7 . Upon selection of a sensor, operators see the anomalies detected during the selected month and can furthermore select a specific day to see the actual values and therefore review the actual anomaly that was detected, as shown in Fig. 8 .

figure 7

Sensor selection

figure 8

Sensor history and details

4.2.4 Results

The obtained boundaries (from step 2 in Sect. 4.2.2 ) could be used for daily analysis of sensors and various visualization tasks, such as showing the number of anomalous measurements for the current day, as seen in Fig. 8 , comparing the number of outliers between two sensors for the given time window, etc., as shown in Fig. 9 .

figure 9

Number of outliers between sensors

5 Discussion

Reflecting on CRF’s experience and all the work done within the I-BiDaaS Project, this section develops several recommendations addressed to any manufacturing company willing to undertake Big Data projects. This section also positions the I-BiDaaS solution within Big Data Value (BDV) reference model and Strategic Research and Innovation Agenda (SRIA).

5.1 Lessons Learned, Challenges and Guidelines

The I-BiDaaS project developed an integrated platform for processing and extracting actionable knowledge from Big Data in the manufacturing sector. Based on the challenges experienced and lessons learned through our involvement in I-BiDaaS, we propose a set of guidelines for the implementation of Big Data analytics in the manufacturing sector, with respect to the following concerns:

Data storage and ingestion from various data sources and its preparation: In a production line deploying digital instruments, there are many devices which setup operating values and adjust and control parameters during the production processes. Depending on whether we want to act on the quality of the production process or on the maintenance of the equipment, the first challenge is to understand how data will be ingested and managed from data sources over time and who will be able to access them. Furthermore, this aspect highlights the importance of breaking data silos by extracting the value of all data collected from several sources and levels and may be necessary to involve different departments belonging to the same or different organizations.

Data cleaning: A second important aspect is to understand which types of data can be useful for analysis. This implies the importance of data cleaning in order to identify incomplete, inaccurate and irrelevant parts of the generated dataset.

Fabrication of realistic synthetic data for experimentation and testing:

Data are strictly confidential, so another challenge is to decide how data will be shared if external analysis is required. In this case, manufacturers need to evaluate the possibility of fabrication of realistic synthetic data for experimentation of the analytical models that will be developed and then to test the same models with anonymized real data.

Batch and stream analytics for increasing the speed of data analysis: After collecting and analysing data, it is necessary to understand which Big Data technologies are most suitable for the specific identified business requirements. Batch and stream analytics cover all aspects, which may occur in real-world environments, including cases that require a deeper analysis of large amounts of data collected over a period of time (batch) or those that require velocity and agility for the events that we need to monitor in real or near-real-time (streaming).

Simple, intuitive and effective visualization of results and interaction capabilities for the end-users: Advanced visualization tools which provide the insights, value and operational knowledge extracted from available data need to consider both expert and non-expert end-users (e.g. manufacturers, engineers and operators)

5.2 Connection to BDV Reference Model, BDV SRIA, and AI, Data and Robotics SRIDA

The described solution for the defined manufacturing use cases can be contextualized within the BDV reference model defined in the BDV Strategic Research and Innovation Agenda (BDV SRIA). They contribute to the BDV reference model in the following ways. Specifically, regarding the BDV reference model horizontal concerns, we address:

Data visualization and user interaction : By developing several advanced and interactive visualization solutions applicable in the manufacturing sector, as detailed in Sects. 4.1.3 and 4.2.3 .

Data analytics : By developing data analytics solutions for the two industrial use cases in the manufacturing sector, as described in Sects. 4.1.2 and 4.2.2 . While the solutions may not correspond to state-of-the-art advances in AI/machine learning algorithms development, they clearly contribute to revealing novel insights and best practices on how Big Data analytics can improve manufacturing operations.

Data processing architectures : We develop architectures as shown in Figs. 2 and 6 that are well suited for manufacturing applications wherein both batch analytics (e.g. analysing historical data) and streaming analytics (e.g. online processing of the data that correspond to a newly manufactured engine) are required.

Data protection and data management : Real data were anonymized by CRF that manipulated and masked them after they were retrieved from an internal proprietary server.

Regarding the BDV reference model vertical concerns, we address the following:

Big data types and semantics : Our work here is mostly concerned with structured sensory data, meta-data and thermal images data (which corresponds to the Media, Image, Video and Audio data types according to the BDV nomenclature). The work also contributes to best practices in the generation of realistic synthetic data from the corresponding domain-defined meta-data, as well as a systematic way to assess the quality and usefulness of the generated synthetic data.

Communication and connectivity : the work describes innovative ways to communicate with and retrieve data from an internal manufacturing company proprietary server, as described in Sect. 4 and outlined in Fig. 1 .

Therefore, in relation with BDV SRIA, the I-BiDaaS solution contributes to the following technical priorities: Data protection; Data Processing Architectures; Data Analytics; and Data Visualization and User Interaction.

Furthermore, in relation to the BDVA SRIA priority areas in connection with Factories of the Future with EFFRA, we address the following dimensions:

Excellence in manufacturing: advanced manufacturing processes and services for zero-defect and innovative processes and products

Sustainable value networks: manufacturing driving the circular economy

Inter-operable digital manufacturing platforms: supporting an ecosystem of manufacturing services

In more detail, CRF use cases have been selected in order to develop innovative tools and solutions that may ensure better product quality towards zero-defect manufacturing. In particular, the existing production lines may be improved to maximize the quality of their product through the integration of solutions that exploit Big Data technologies. A better process efficiency can result in energy saving and cost reduction in the context of circular economy and allow manufacturers to reach a high level of competitiveness and sustainability.

Finally, the chapter relates to the following cross-sectorial technology enablers of the AI, Data and Robotics Strategic Research, Innovation & Deployment Agenda [ 37 ], namely: Knowledge and Learning, Reasoning and Decision Making, and Systems, Methodologies, Hardware and Tools.

6 Conclusion

The increasing levels of digitalization in the manufacturing sector contribute to generate a large amount of data that often contain a high value of hidden information. This is due to the complexity of real processes that require several interconnected stages to obtain finished goods. Variables and parameters are set for the operation of each digital machine and just like we assemble components, we need to pull together data generated from different sources and levels if we want to improve the quality of processes and products. I-BiDaaS developed an integrated platform, taking into consideration how complex data can be managed and how to help manufacturers who are not sufficiently enabled to analyse complex datasets, by empowering them to easily utilize and interact with Big Data technologies.

As explained below, we identify throughout the chapter several best practices for the application of Big Data analytics in manufacturing.

Visualization with TensorBoard:

Nahm, A., Vonderembse, M., & Koufteros, X. (2003). The impact of organizational structure on time-based manufacturing and plant performance. Journal of Operations Management, 21 , 281–306.

Article   Google Scholar  

Schwab, K. (2016). The fourth industrial revolution . Franco Angeli.

Google Scholar  

Chen, B., Wan, J., Shu, L., Li, P., Mukherjee, M., & Yin, B. (2017). Smart factory of Industry 4.0: Key technologies, application case, and challenges. IEEE Access, 6 , 6505–6519.

Groover, M. P. (2018). Automation, production systems, and computer-integrated manufacturing . Pearson.

Yadegaridehkordi, E., Hourmand, M., Nilashi, M., Shuib, L., Ahani, A., & Ibrahim, O. (2018). Influence of big data adoption on manufacturing companies’ performance: an integrated DEMATEL-ANFIS approach. Technological Forecasting and Social Change, 137 , 199–210.

O’Donovan, P., Leahy, K., Bruton, K., & O’Sullivan, D. T. J. (2015). Big data in manufacturing: A systematic mapping study. Journal of Big Data, 2 , 20.

Passlick, J., Lebek, B., & Breitner, M. H. (2017). A self-service supporting business intelligence and big data analytics architecture. In 13th international conference on Wirtschaftsinformatik, St. Gallen, Switzerland .

Bornschlegl, M. X., Berwind, K., & Hemmje, M. (2017). Modeling end user empowerment in big data applications. In 26th International conference on software engineering and data engineering at: San Diego, CA, USA .

Zillner, S., Curry, E., Metzger, A., Auer, S., & Seidl, R., (Eds.). (2017). European big data value. Strategic research & innovation agenda . Springer.

Arruda, D. (2018). Requirements engineering in the context of big data applications. SIGSOFT Software Engineering Notes, 43 (1), 1–6.

Raguseo, E. (2018). Big data technologies: An empirical investigation on their adoption, benefits and risks for companies. International Journal of Information Management, 38 (1), 187–195.

Nuseibeh, B., & Easterbrook, S. (2000). Requirements engineering: A roadmap. In Proceedings of the conference on the future of software engineering, ICSE’00 (pp. 35–46).

Paech, B., Dutoit, A. H., Kerkow, D., & Von Knethen, A. (2002). Functional requirements, non-functional requirements, and architecture should not be separated—A position paper. In Proceedings of the 8th international working conference on requirements engineering .

Horkoff, J., Aydemir, F. B., Cardoso, E., Li, T., Maté, A., Paja, E., Salnitri, M., Piras, L., Mylopoulos, J., & Giorgini, P. (2019). Goal-oriented requirements engineering: An extended systematic mapping study. Requirements Engineering, 24 , 133–160.

I-BiDaaS Consortium. (2018). D1.3: Positioning of I-BiDaaS. Available at: .

Murray, M. T., & Murray, M. (2011). High pressure die casting of aluminium and its alloys. In Fundamentals of aluminium metallurgy production, processing and applications . Woodhead Publishing series in metals and surface engineering (pp. 217–261).

Lumley, R. N. (2011). Progress on the heat treatment of high pressure die castings. In Fundamentals of aluminium metallurgy production, processing and applications . Woodhead Publishing series in metals and surface engineering (pp. 262–303).

Winkler, M., Kallien, L., & Feyertag, T. (2015). Correlation between process parameters and quality characteristics in aluminum high pressure die casting. In Conference: NADCA .

Fiorese, E., & Bonollo, F. (2016). Process parameters affecting quality of high-pressure die-cast Al-Si alloy . Doctoral Thesis, University of Padova.

Chandrasekaran, R., Campilho, R. D. S. G., & Silva, F. J. G. (2019). Reduction of scrap percentage of cast parts by optimizing the process parameters. Procedia Manufacturing, 38 , 1050–1057.

Bhuiyan, M. S. H., & Choudhury, I. A. (2014). Review of sensor applications in tool condition monitoring in machining. Reference Module in Materials Science and Materials Engineering, Comprehensive Materials Processing, 13 , 539–569.

Borgi, T., Hidri, A., Neef, B., & Nauceur, M. S. (2017). Data analytics for predictive maintenance of industrial robots. In International conference on advanced systems and electric technologies (IC_ASET) .

Eren, H. (2012). Assessing the health of sensors using data historians. In IEEE sensors applications symposium proceedings .

Dal, B., Tugwell, P., & Greatbanks, R. (2000). Overall equipment effectiveness as a measure of operational improvement—A practical analysis. International Journal of Operations & Production Management, 20 (12), 1488–1502.

Ljungberg, Õ. (1998). Measurement of overall equipment effectiveness as a basis for TPM activities. International Journal of Operations & Production Management, 18 (5), 495–507(13).

Galar, D., Sandborn, P., & Kumar, U. (2017). Maintenance costs and life cycle cost analysis . CRC Press.

Arapakis, I., Becerra, Y., Boehm, O., Bravos, G., Chatzigiannakis, V., Cugnasco, C., Demetriou, G., Eleftheriou, I., Mascolo, J. E., Fodor, L., Ioannidis, S., Jakovetic, D., Kallipolitis, L., Kavakli, E., Kopanaki, D., Kourtellis, N., Marcos, M. M., de Pozuelo, R. M., Milosevic, N., Morandi, G., Montanera, E. P., & Ristow, G. H. (2019). Towards specification of a software architecture for cross-sectoral big data applications. In IEEE world congress on services (SERVICES) (Vol. 2642). IEEE.

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

MATH   Google Scholar  

Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., & Chen, T. (2018). Recent advances in convolutional neural networks. Pattern Recognition, 77 , 354–377.

Huang, G., Liu, Z., Van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4700–4708).

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 770–778).

I-BiDaaS Consortium. (2020). D3.3: Batch Processing Analytics module implementation final report. Available at:

Bock, H. H. (2017). Clustering methods: a history of k-means algorithms. In Selected contributions in data analysis and classification . Springer (pp. 161–172).

Snoke, J., Raab, G. M., Nowok, B., Dibben, C., & Slavkovic, A. (2016). General and specific utility measures for synthetic data. Journal of the Royal Statistical Society Series A (Statistics in Society), 181 (3).

Gupta, M., Gao, J., Aggarwal, C. C., & Han, J. (2014). Outlier detection for temporal data: a survey. IEEE Transactions on Knowledge and Data Engineering, 26 (9), 2250–2267.

Petitjean, F., Forestier, G., Webb, G. I., Nicholson, A. E., Chen, Y., & Keogh, E. (2014). Dynamic time warping averaging of time series allows faster and more accurate classification. In IEEE international conference on data mining .

Zillner, S., Bisset, D., Milano, M., Curry, E., García Robles, A., Hahn, T., Irgens, M., Lafrenz, R., Liepert, B., O’Sullivan, B., & Smeulders, A. (Eds.) (2020, September). Strategic research, innovation and deployment agenda—AI, data and robotics partnership . Third release. Brussels. BDVA, euRobotics, ELLIS, EurAI and CLAIRE.

Download references


The work presented in this chapter is supported by the I-BiDaaS project, funded by the European Union’s Horizon 2020 research and innovation programme under Grant Agreement 780787. This publication reflects the views only of the authors, and the Commission cannot be held responsible for any use which may be made of the information contained therein.

Author information

Authors and affiliations.

Aegis IT Research LTD, London, UK

Andreas Alexopoulos, Spiros Fotis, Leonidas Kallipolitis & Ilias Spais

Barcelona Supercomputing Center, Barcelona, Spain

Yolanda Becerra, Cesare Cugnasco, Miquel Martínez & Raül Sirvent

IBM, Haifa, Israel

Omer Boehm & Michael Vinov

Information Technology for Market Leadership, Athens, Greece

George Bravos & Vassilis Chatzigiannakis

Ecole des Ponts ParisTech, Champs-sur-Marne, France

Giorgos Demetriou, Vlatka Katusic & Hernan Ruiz-Ocampo

University of Manchester, Manchester, UK

Iliada Eleftheriou, Evangelia Kavakli & Rizos Sakellariou

Centro Ricerche FIAT, Orbassano, Italy

Gianmarco Genchi, Julien Mascolo & Giuseppe Danilo Spennacchio

Technical University of Crete - School of Electrical and Computer Engineering, Crete, Greece

Sotiris Ioannidis

Foundation for Research and Technology, Hellas - Institute of Computer Science, Crete, Greece

Sotiris Ioannidis, Despina Kopanaki, Christoforos Leventis & Giorgos Vasiliadis

University of Novi Sad - Faculty of Sciences, Novi Sad, Serbia

Dusan Jakovetic, Nemanja Milosevic, Srdjan Skrbic & Dusan Stamenkovic

ATOS, Madrid, Spain

Enric Pere Pages Montanera

Software AG, Darmstadt, Germany

Gerald Ristow

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Giuseppe Danilo Spennacchio .

Editor information

Editors and affiliations.

Insight SFI Research Centre for Data Analytics, NUI Galway, Ireland

Edward Curry

Information Centre for Science and Technology, Leibniz University Hannover, Hannover, Germany

SINTEF Digital, Oslo, Norway

Arne J. Berre

Paluno, University of Duisburg-Essen, Essen, Germany

Andreas Metzger

Universidad Politécnica de Madrid, Boadilla del Monte, Madrid, Spain

Maria S. Perez

Siemens Corporate Technology, München, Germany

Sonja Zillner

Rights and permissions

Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License ( ), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

Reprints and permissions

Copyright information

© 2022 The Author(s)

About this chapter

Cite this chapter.

Alexopoulos, A. et al. (2022). Big Data Analytics in the Manufacturing Sector: Guidelines and Lessons Learned Through the Centro Ricerche FIAT (CRF) Case. In: Curry, E., Auer, S., Berre, A.J., Metzger, A., Perez, M.S., Zillner, S. (eds) Technologies and Applications for Big Data Value . Springer, Cham.

Download citation


Published : 29 April 2022

Publisher Name : Springer, Cham

Print ISBN : 978-3-030-78306-8

Online ISBN : 978-3-030-78307-5

eBook Packages : Computer Science Computer Science (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

trg logo

Data Analytics for Manufacturing: the Tesla’s Case Study (Part 1)

Posted by Thai Pham on Sun, Apr 30, 2017

If Tesla Motors is to achieve the aggressive goal of making 1 million cars by 2020 set out by its CEO Elon Musk, it will partly be because of the application of data analytics in its manufacturing operations.

Data analytics for manufacturing

  • Blindness to data

Tableau’s advantages

Looking at data from different angles, process monitoring.

This April marked a historic moment for the automotive industry when Tesla briefly became the US’ most valuable carmaker. Its market capitalisation reached US$51 billion on April 10, surpassing US$50 billion of General Motors (GM) and US$45 billion of Ford.

Why do investors value Elon Musk’s electric car manufacturer more than GM and Ford even though Tesla’s 2016 sales volume was only 76,000 vehicles, a fraction of Ford’s (6.6 million) and GM’s (10 million), and it is still in the red, posting a net loss of US$675 million last year?

Tesla’s CEO - Elon Musk

Musk’s bold vision for the future of transportation, in which all vehicles will eventually be all-electric and fully autonomous, certainly plays an important part. To make that vision a reality, CEO Elon Musk has set ambitious goals for Tesla for production capacity.

Subscribe to TRG Blog

In 2013, Tesla delivered just around 20,000 Model S full-size sedans, the company’s first series production vehicle. 3 years later, the annual production rate reached 100,000. And Elon Musk is aiming to deliver 500,000 vehicles by 2018 and 1,000,000 by 2020.

Last December, the city of Fremont, California, approved Tesla’s plans to double the size of its factory there. There will be an additional 420,000 square meters of manufacturing space. And the number of workers is expected to increase from 6,000 to 9,000.


This massive expansion is crucial as Tesla’s product line continues to grow rapidly. Prior to 2015, the Fremont factory only built the Model S, which was later joined by the Model X SUV. Production of the more affordable Model 3 is scheduled to commence later this year. At present, Tesla has received over 370,000 pre-orders for Model 3.

Such rapid production growth and aggressive goals can undoubtedly create a lot of chaos. And Tesla is no stranger to missed deadlines. According to the Wall Street Journal, the company has failed to meet its projections more than 20 times in the past 5 years. As part of the ongoing effort to tame chaos and improve manufacturing efficiency, Tesla has turned to advanced data analytics software .

Back to the top

Tesla production data is fed into several different key systems. The first major one is in the MES (Manufacturing Execution System). This software essentially is the air traffic controller of the entire production process. It can tell a certain item in the assembly line where it should be heading, keep track of the production orders and quality issues, and collect basic measurements. The MES uses Oracle/SQL Server databases.

More in-depth and customised test data is stored in a separate MySQL Test database which was developed by Tesla’s in-house dev team. Additionally, the web-enabled QuickBase is also used to track process changes and ongoing quality issues due to its flexibility and ease of use. And finally, Excel spreadsheets are used for one-off manual reports. 

Not only does data go into many different places, but it also has to serve highly diverse audiences, who have very different interests. Whereas people working in Production care about yield and rework calculation, people in Equipment Sustaining may care about preventive maintenance, and people in Process Sustaining are interested in root cause investigation. Sometimes, people do not know where to get the data they need.

Read more: Business Intelligence in the Manufacturing Industry

Data Analytics for Manufacturing: the Tesla’s Case Study

‘Blindness to data’

Apart from a wide variety of databases and data reporting needs, there were plenty of different tools employed by Tesla staff. Most relied on Excel or an in-house app built on LabView, and a select few knew how to use MySQL Workbench or R.

This situation caused a lot of frustration when people had a hard time looking for the right data. Bottlenecks were created since only a handful of people had direct access to most data as well as the expertise to use advanced data analytics tools. And because the majority of staff had to use Excel for data handling, the process was slow and inefficient. Consequently, people were often unaware of what was going on in other parts of the production line.

The top data reporting needs are:

  • Production counts and yield
  • Quality defect tracking/analysis
  • Statistical Process Control (SPC) and Process monitoring
  • Root-cause investigation
  • Open-ended data exploration
  • Statistical analysis - DOE, GRR, etc.

It is worth noting that most of these reporting needs are heavy on data visualisation and data exploration rather than on statistics and scripting. This played an important part in Tesla’s decision to adopt Tableau data analytics software .

Read more: 3 Best Business Intelligence & Analytics Vendors 2017

Data Analytics for Manufacturing: the Tesla’s Case Study

One distinct advantage of Tableau is “data source agnostic”, i.e. users no longer have to care where the data comes from. They can pull any data from any source at any time. They can view data located in MES, Test DB, QuickBase or Excel files side-by-side on the same dashboard.

Tableau also allows ordinary users, even those who are not programmers, to easily create powerful and tailored visualisations. Before that, they would have had to spend at least 6 months learning R to build such data visualisations.

Another huge improvement brought about by Tableau is publishing and sharing. In the past, those capable of using analytics tools often had to export their works and send them to others via email. This approach was time-consuming and lacked interactions. Conversely, Tableau users can easily publish their works and let others interact with them on their web browsers.

In the next sections, we will explore some applications of Tableau in building production reporting tools at the Tesla factory.

To have a complete picture, people need to be able to look at and drill down data from multiple angles. Then trends and patterns are much easier to detect.

The following visualisation workbook shows 3 different views of a single set of data: the number of quality issues.

Data Analytics for Manufacturing: the Tesla’s Case Study

The top left visualisation shows the defect counts over time. The top right visualisation counts the number of defects by work centres. And at the bottom right corner is the visualisation of defects by categories.

Users from Process Sustaining use this workbook in their day-to-day jobs. They can drill down the data in any way they want. For instance, they can easily see the number of defects in each work centre by dates and by categories just by clicking on that particular work centre.

Data Analytics for Manufacturing: the Tesla’s Case Study

Then they can filter down even further by clicking on a defect category and see the number of that specific defect type over time.

Data Analytics for Manufacturing: the Tesla’s Case Study

The bottom left corner is where users can see the detailed information on each quality defect, including notes from individuals who conducted the inspection. So users can perform a context drill-down from high-level data to individual serial numbers on the same screen.

Data Analytics for Manufacturing: the Tesla’s Case Study

The following dashboard monitors the number of false part rejects, which happen when parts are scanned by barcode scanners and falsely rejected. This could be due to several reasons. The parts may not be held at the right angle towards the scanners or the scanners are misaligned. 

The following dashboard shows data from 19 work centres (MAC01 to MAC19); each has 10 nests (A to J) where the barcodes are scanned. The false reject rates are represented by colours. A green nest means the false reject rate is within the limit.

Data Analytics for Manufacturing: the Tesla’s Case Study

Users can click on one particular work centre and see the trends of false rejects of individual nests over time. More important, they can pull equipment logs of the same period of time from a separate database and see if someone has already logged the scanners down and alerted the maintenance crew and if the false reject rate of a scanner has dropped after it was repaired.


In this particular case, there were 2 maintenance alerts put in for the scanner of nest B / work centre MAC14. And the rate has gone down after the 2 nd repair.

The point of such process monitoring is to be able to see not only what is going on but also the deeper context of the actions taken.

This is the 1 st part of our article. Please  read the second part  or  subscribe to our blog for the latest content about Business Intelligence and Analytics. 

You can also request a Tableau demo to see how this solution can help your business.

Tableau BI Demo

Topics: Business Intelligence , Analytics

  • The Use of Spreadsheets and Modern Cloud Adoption in Businesses
  • Infor SaaS: The Trusted Cloud Infrastructure for Your Business Solutions
  • Proper Data Preparation: Key Ingredient Ensuring a Smooth Cloud Migration
  • The Popularisation of AI-Powered Applications: Should You Be Afraid of ChatGPT?
  • 5 Ways Infor ION Can Transform Your Enterprise
  • Infor Coleman AI Wins Prestigious Stratus Award for Artificial Intelligence

Subscribe to TRG Blog

Posts by topic.

  • Amazon Web Services (1)
  • Analytics (68)
  • Business Intelligence (72)
  • Cloud Computing (98)
  • Cloud OS (1)
  • cybersecurity (8)
  • Digital Transformation (54)
  • digital workplace (2)
  • Enterprise Performance Management (EPM) (110)
  • Enterprise Resource Planning ERP (148)
  • Financial Accounting Management Software (286)
  • Financial consolidation, planning and reporting (111)
  • Hospitality solutions (98)
  • Inbound marketing (4)
  • Infor SunSystems (90)
  • Planning and Budgeting (68)
  • project management (1)
  • Retail Management System (130)
  • Rick Yvanovich (1)
  • Talent Management (318)
  • Technology trends (112)

Upcoming TRG Events

Latest Posts

Most viewed posts, our editorial mission.

rick yvanovich resized 174

With TRG International Blogs, it is our mission to be your preferred partner providing solutions that work and we will make sure to guide your business to greatness every day.

TRG Logo

IT, Talent and F&B - we think it's a great combination.

We've thrived since 1994 resulting in lots of experience to share, we are beyond a companion, to more than 1,000 clients in 80+ countries.

Follow us on Social Media

Enterprise solutions.

  • Financial Management
  • Hospitality
  • Resource Planning (ERP)
  • BI & Analytics
  • Retail Management
  • Performance Management

Talent Solutions

  • Recruitment
  • Training & Development
  • Sales & Customer Services
  • Retention & Engagement
  • Customised Solution
  • Join our team
  • Urgent Vacancies
  • Internships
  • Career Days
  • Be our partner

Partner logo

© 2023 TRG International. Privacy Policy   /   Тerms & Conditions   /   Site map   /   Contact Us

TRG encourages websites and blogs to link to its web pages. Articles may be republished without alteration with the attribution statement "This article was first published by TRG International (" and a clickable link back to the website. We are changing support for TLS 1.0 and older browsers. Please check our list of supported browsers.

Google Analytics


14 Fascinating Case Studies of Manufacturing Analytics in Action

' src=

Hi there! As a fellow data analytics enthusiast, I wanted to share some captivating real-world examples that showcase the power of analytics in manufacturing. These case studies highlight how leading manufacturers across sub-sectors and geographies are utilizing data to optimize processes and improve performance. Let‘s examine these success stories closer to uncover the tangible benefits and key learnings.

The Growing Importance of Manufacturing Analytics

The manufacturing sector is undergoing a technology-fueled transformation. According to IDC, manufacturing accounted for 11% of the $215 billion spent on big data and analytics solutions in 2022. With the proliferation of industrial internet of things (IIoT) and advances in artificial intelligence (AI), manufacturers now have access to a wealth of structured and unstructured data. This data holds precious insights that can drive transformative outcomes when processed through advanced analytics.

Specifically, manufacturing analytics applications leverage predictive modeling, machine learning, digital twin simulations and other techniques to improve uptime, quality, productivity, compliance and more. A survey by LNS Research found that manufacturers deploying these solutions averaged:

  • 20% improvement in cycle time
  • 25% reduction in maintenance costs
  • 15% increase in production yield

Let‘s explore real-world examples that bring these statistics to life.

Optimizing Energy Usage at an Italian Packaging Company

SIG is a leading European supplier of aseptic carton packaging with a large production facility in Italy. The rising costs of energy like gas and electricity prompted SIG to deploy a manufacturing analytics solution to optimize consumption.

The analytics software ingested data from over 200 sensors and meters spread across the facility‘s production lines. Machine learning algorithms identified areas of excess energy usage by comparing patterns across equipment. For example, compressed air leaks in some machines caused a spike in electricity consumption.

By monitoring energy KPIs in real-time and getting granular visibility into consumption, SIG optimized equipment operating conditions. Fixing air leaks alone resulted in reducing the plant‘s electricity costs by 2.5%. Overall, the manufacturing analytics implementation led to $400,000 in annual savings through energy optimization.

Early Defect Detection in Auto Component Manufacturing

A Tier-1 automotive component supplier in Germany was grappling with quality issues leading to rising warranty costs. They partnered with an AI vendor to deploy computer vision analytics on their production lines.

High-resolution cameras captured images of manufactured components like gears, cylinders, axles etc. These images fed into machine learning models that had been trained to identify minute defects like scratches or dents. The models also categorized the defects and flagged them in real-time to quality technicians.

By detecting quality issues instantly rather than at end-of-line inspection, the root causes could be addressed promptly. This resulted in a 37% decrease in defects within three months. The insights also helped optimize production processes and reduce warranty claims by over 55% in a year.

Transforming Maintenance at a Leading Aerospace Manufacturer

UTC Aerospace Systems creates various aircraft components like landing gear brakes and sensors. The repetitive stress on equipment led to frequent breakdowns, impacting production schedules. To predict and prevent failures, they adopted a manufacturing analytics approach powered by machine learning.

Sensors were installed to collect vibration, temperature and other data across machinery like hydraulic presses and machining tools. The analytics software analyzed this time-series data to identify patterns indicative of imminent failures. Technicians were alerted proactively so that issues could be prevented through maintenance.

This shift from preventive to predictive maintenance drastically reduced equipment downtime. Parts longevity also improved with timely repairs. Overall equipment effectiveness (OEE) at the plant increased by over 8% within nine months.

Driving Overall Equipment Effectiveness (OEE) in Automotive Manufacturing

BMW‘s automobile manufacturing plant in South Carolina, USA produces 1,500 vehicles daily. By leveraging IIoT and manufacturing analytics, BMW aimed to maximize OEE and optimize productivity across the factory floor.

Hundreds of robots, CNC machines, conveyors and other connected equipment generated vast volumes of operational data. Analytics algorithms processed this real-time data to provide shop floor visibility through digital twin models.

Managers used these actionable insights to identify bottlenecks like delayed material handling. By being agile and addressing issues quicker, OEE improved by 11% within a year. Assembly line productivity also rose by around 8%.

Transforming Maintenance Processes in Wind Turbine Manufacturing

Vestas is a leading turbine manufacturer serving the wind energy industry. The moving components inside turbines often broke down, affecting availability and power generation. Vestas adopted manufacturing analytics to pivot from periodic to predictive servicing of turbines.

Sensors were installed to monitor temperature, vibration and other metrics across critical turbine parts. The analytics model processed this data to detect potential failures and prescribe corrective steps to avoid them.

With issues forecasted further in advance, technicians could address problems before they escalated. The analytics adoption resulted in a 30% decrease in turbine downtime over two years. It also cut maintenance costs by 20% and extended machinery lifespan.

Maximizing Die Tool Utilization

Hirotec, a leading auto component manufacturer in Japan, wanted to optimize their large die tooling operations spread across multiple locations. Manual monitoring of tool usage led to excess inventory and maintenance costs.

By connecting each die tooling machine to IIoT sensors and gateways, operational data was unified on a cloud platform. Manufacturing analytics generated insights on tool usage intensity, lifecycle stage and maintenance needs.

With real-time visibility into die tool health and utilization, planning improved considerably. Die tool inventory was right-sized, leading to $3 million in cost savings. Overall equipment effectiveness also rose by over 7% in a year.

Takeaways from These Case Studies

These examples showcase how organizations across sub-sectors like automotive, aerospace, packaging and more are benefiting from manufacturing analytics. Though their use cases differ, we observe a few common themes:

Transitioning from preventive to predictive maintenance – Sensor data and machine learning models enable failure forecasting and minimize downtime. This leads to improved asset availability and lifespan.

Early defect detection – Analytics performs real-time quality monitoring at the component-level to minimize rework. Production processes also improve through data-driven insights.

Increasing Overall Equipment Effectiveness – By identifying and addressing bottlenecks in real-time, analytics drives productivity and efficiency.

Optimizing energy usage – Granular visibility into energy consumption enables monitoring, control and cost reduction.

Inventory and asset optimization – Unified data gives inventory and asset visibility for right-sizing and cost savings.

As IIoT proliferation and analytics techniques continue maturing, manufacturing intelligence will become integral to long-term competitiveness and profitability. With a powerful stack of data management, industrial automation and advanced analytics, manufacturers can pivot towards true smart factory paradigms.

I hope these real-world examples provided helpful context on the tangible outcomes enabled by manufacturing analytics. Let me know if you would like to discuss current use cases and solution options suitable for your production environment. I‘m always happy to chat more about leveraging data analytics to drive manufacturing excellence!

' src=

I am Paul Christiano, a fervent explorer at the intersection of artificial intelligence, machine learning, and their broader implications for society. Renowned as a leading figure in AI safety research, my passion lies in ensuring that the exponential powers of AI are harnessed for the greater good. Throughout my career, I've grappled with the challenges of aligning machine learning systems with human ethics and values. My work is driven by a belief that as AI becomes an even more integral part of our world, it's imperative to build systems that are transparent, trustworthy, and beneficial. I'm honored to be a part of the global effort to guide AI towards a future that prioritizes safety and the betterment of humanity.

Similar Posts

15+ ai applications, use cases & examples in finance (2023).

Artificial intelligence (AI) has the potential to completely transform the finance industry. According to Insider Intelligence,…

How AI is Transforming Insurance Underwriting in 2023 and Beyond

Underwriting is the crucial process where insurance carriers assess risk profiles and determine pricing. But legacy…

How to Skyrocket Your B2B Demand Generation in 2023

If you run marketing or sales for a B2B company, demand generation is likely a top…

How to Use ChatGPT as a Language Translation Tool: An AI Expert‘s Perspective

ChatGPT‘s translation capabilities have captivated millions of users. But how exactly does this AI chatbot convert…

Synthetic Data for Healthcare: Benefits & Case Studies in 2023

Synthetic data has the power to transform healthcare by enabling innovation in artificial intelligence while still…

ChatGPT in Audit: 5 Use Cases, Benefits & Challenges in 2023

ChatGPT, the viral conversational AI system developed by Anthropic, has sparked excitement – and debate –…


Data Analytics in Manufacturing

Empowering Industry Transformation through Data-Driven Insights

ScatterPie Analytics empowers manufacturers with advanced analytics, AI, and ML solutions to optimize efficiency and scalability in today’s dynamic manufacturing landscape.

case study big data analytics in manufacturing

Why Choose Scatterpie?

case study big data analytics in manufacturing

Official Tableau Partner

Extensive experience of working with fortune manufacturing giants, projects completed, experienced team of data engineers & data analytics, data challenges.

case study big data analytics in manufacturing

Operational Inefficiencies

Data analytics identifies the inefficiencies in manufacturing processes, streamlining operations for enhanced efficiency and productivity.

case study big data analytics in manufacturing

Quality Control

Real-time data analytics ensures consistent product quality by detecting issues early and adhering to quality standards.

case study big data analytics in manufacturing

Demand Forecasting

Accurate demand forecasts optimize production, inventory management, and resource allocation.

case study big data analytics in manufacturing

Supply Chain Complexity

Data analytics optimizes supply chain performance, improving collaboration with suppliers and streamlining logistics.

case study big data analytics in manufacturing

Equipment Maintenance & Downtime

Predictive maintenance reduces downtime, improves equipment utilization, and extends lifespan.

case study big data analytics in manufacturing

Compliance and Risk Management

Data analytics monitors compliance, identifies risks, and develops risk mitigation strategies.

Manufacturing Data Analytics Solutions

Drive efficiency, productivity, and growth with analytics in manufacturing.

At Scatterpie Analytics, we go beyond generating mere data analysis reports. We provide manufacturers with actionable insights that empower decision-making at all levels of the organization. Our end-to-end analytics services offer the following advantages:

Real-Time Visibility:

Manufacturers gain real-time visibility into critical production metrics, inventory levels, and supply chain performance, enabling them to make informed decisions and respond swiftly to market dynamics.

Performance Dashboards:

Through intuitive dashboards and reports, executives gain access to key performance indicators (KPIs), enabling them to monitor progress, identify trends, and drive strategic initiatives with confidence.

Predictive Analytics:

Our advanced predictive analytics models empower manufacturers to forecast demand, optimize production schedules, and mitigate potential bottlenecks, ensuring timely delivery and superior customer satisfaction.

case study big data analytics in manufacturing

Prescriptive Analytics

By leveraging prescriptive analytics, manufacturers can optimize pricing strategies, identify cost-saving opportunities, and improve resource allocation, maximizing profitability and competitive advantage.

Data-Driven Continuous Improvement

With our analytics insights, manufacturers can foster a culture of continuous improvement, identifying process inefficiencies, optimizing workflows, and driving innovation throughout the organization.

AI-Driven Quality and Safety Solutions:

We help manufacturers harness the power of AI-driven analytics to revolutionize quality control and safety in manufacturing. Companies can leverage advanced algorithms to detect anomalies, enhance defect detection, and ensure a safe working environment, driving unparalleled quality and safety standards.

case study big data analytics in manufacturing

Our Manufacturing Clientele

case study big data analytics in manufacturing

Our Partner Technology

case study big data analytics in manufacturing

Empower Your Manufacturing with Data Analytics

Featured insights.

  • Pharmaceuticals Industry
  • Cement Indusrty
  • Tyre Industry

Data Analytics in Pharmaceutical Industry

Enhance Efficiency: Supply Chain Analytics in Manufacturing

July 27, 2023

Predictive Analytics in Manufacturing Industry

How Predictive Analytics in Manufacturing is Transforming Operations

What is Manufacturing Analytics

Reasons to Add Analytics in Manufacturing

April 20, 2023

benchmarking kpi

A Deep Dive into Comparing and Benchmarking KPI

April 14, 2023

We Use Cookies

Privacy overview.

Big Data Analytics for Predictive Manufacturing Control - A Case Study from Process Industry

Ieee account.

  • Change Username/Password
  • Update Address

Purchase Details

  • Payment Options
  • Order History
  • View Purchased Documents

Profile Information

  • Communications Preferences
  • Profession and Education
  • Technical Interests
  • US & Canada: +1 800 678 4333
  • Worldwide: +1 732 981 0060
  • Contact & Support
  • About IEEE Xplore
  • Accessibility
  • Terms of Use
  • Nondiscrimination Policy
  • Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

The Philippines economy in 2024: Stronger for longer?

The Philippines ended 2023 on a high note, being the fastest growing economy across Southeast Asia with a growth rate of 5.6 percent—just shy of the government's target of 6.0 to 7.0 percent. 1 “National accounts,” Philippine Statistics Authority, January 31, 2024; "Philippine economic updates,” Bangko Sentral ng Pilipinas, November 16, 2023. Should projections hold, the Philippines is expected to, once again, show significant growth in 2024, demonstrating its resilience despite various global economic pressures (Exhibit 1). 2 “Economic forecast 2024,” International Monetary Fund, November 1, 2023; McKinsey analysis.

The growth in the Philippine economy in 2023 was driven by a resumption in commercial activities, public infrastructure spending, and growth in digital financial services. Most sectors grew, with transportation and storage (13 percent), construction (9 percent), and financial services (9 percent), performing the best (Exhibit 2). 3 “National accounts,” Philippine Statistics Authority, January 31, 2024. While the country's trade deficit narrowed in 2023, it remains elevated at $52 billion due to slowing global demand and geopolitical uncertainties. 4 “Highlights of the Philippine export and import statistics,” Philippine Statistics Authority, January 28, 2024. Looking ahead to 2024, the current economic forecast for the Philippines projects a GDP growth of between 5 and 6 percent.

Inflation rates are expected to temper between 3.2 and 3.6 percent in 2024 after ending 2023 at 6.0 percent, above the 2.0 to 4.0 percent target range set by the government. 5 “Nomura downgrades Philippine 2024 growth forecast,” Nomura, September 11, 2023; “IMF raises Philippine growth rate forecast,” International Monetary Fund, July 16, 2023.

For the purposes of this article, most of the statistics used for our analysis have come from a common thread of sources. These include the Central Bank of the Philippines (Bangko Sentral ng Pilipinas); the Department of Energy Philippines; the IT and Business Process Association of the Philippines (IBPAP); and the Philippines Statistics Authority.

The state of the Philippine economy across seven major sectors and themes

In the article, we explore the 2024 outlook for seven key sectors and themes, what may affect each of them in the coming year, and what could potentially unlock continued growth.

Financial services

The recovery of the financial services sector appears on track as year-on-year growth rates stabilize. 6 Philippines Statistics Authority, November 2023; McKinsey in partnership with Oxford Economics, November 2023. In 2024, this sector will likely continue to grow, though at a slower pace of about 5 percent.

Financial inclusion and digitalization are contributing to growth in this sector in 2024, even if new challenges emerge. Various factors are expected to impact this sector:

  • Inclusive finance: Bangko Sentral ng Pilipinas continues to invest in financial inclusion initiatives. For example, basic deposit accounts (BDAs) reached $22 million in 2023 and banking penetration improved, with the proportion of adults with formal bank accounts increasing from 29 percent in 2019 to 56 percent in 2021. 7 “Financial inclusion dashboard: First quarter 2023,” Bangko Sentral ng Pilipinas, February 6, 2024.
  • Digital adoption: Digital channels are expected to continue to grow, with data showing that 60 percent of adults who have a mobile phone and internet access have done a digital financial transaction. 8 “Financial inclusion dashboard: First quarter 2023,” Bangko Sentral ng Pilipinas, February 6, 2024. Businesses in this sector, however, will need to remain vigilant in navigating cybersecurity and fraud risks.
  • Unsecured lending growth: Growth in unsecured lending is expected to continue, but at a slower pace than the past two to three years. For example, unsecured retail lending for the banking system alone grew by 27 percent annually from 2020 to 2022. 9 “Loan accounts: As of first quarter 2023,” Bangko Sentral ng Pilipinas, February 6, 2024; "Global banking pools,” McKinsey, November 2023. Businesses in this field are, however, expected to recalibrate their risk profiling models as segments with high nonperforming loans emerge.
  • High interest rates: Key interest rates are expected to decline in the second half of 2024, creating more accommodating borrowing conditions that could boost wholesale and corporate loans.

Supportive frameworks have a pivotal role to play in unlocking growth in this sector to meet the ever-increasing demand from the financially underserved. For example, financial literacy programs and easier-to-access accounts—such as BDAs—are some measures that can help widen market access to financial services. Continued efforts are being made to build an open finance framework that could serve the needs of the unbanked population, as well as a unified credit scoring mechanism to increase the ability of historically under-financed segments, such as small and medium-sized enterprises (SMEs), to access formal credit. 10 “BSP launches credit scoring model,” Bangko Sentral ng Pilipinas, April 26, 2023.

Energy and Power

The outlook for the energy sector seems positive, with the potential to grow by 7 percent in 2024 as the country focuses on renewable energy generation. 11 McKinsey analysis based on input from industry experts. Currently, stakeholders are focused on increasing energy security, particularly on importing liquefied natural gas (LNG) to meet power plants’ requirements as production in one of the country’s main sources of natural gas, the Malampaya gas field, declines. 12 Myrna M. Velasco, “Malampaya gas field prod’n declines steeply in 2021,” Manila Bulletin , July 9, 2022. High global inflation and the fact that the Philippines is a net fuel importer are impacting electricity prices and the build-out of planned renewable energy projects. Recent regulatory moves to remove foreign ownership limits on exploration, development, and utilization of renewable energy resources could possibly accelerate growth in the country’s energy and power sector. 13 “RA 11659,” Department of Energy Philippines, June 8, 2023.

Gas, renewables, and transmission are potential growth drivers for the sector. Upgrading power grids so that they become more flexible and better able to cope with the intermittent electricity supply that comes with renewables will be critical as the sector pivots toward renewable energy. A recent coal moratorium may position natural gas as a transition fuel—this could stimulate exploration and production investments for new, indigenous natural gas fields, gas pipeline infrastructure, and LNG import terminal projects. 14 Philippine energy plan 2020–2040, Department of Energy Philippines, June 10, 2022; Power development plan 2020–2040 , Department of Energy Philippines, 2021. The increasing momentum of green energy auctions could facilitate the development of renewables at scale, as the country targets 35 percent share of renewables by 2030. 15 Power development plan 2020–2040 , 2022.

Growth in the healthcare industry may slow to 2.8 percent in 2024, while pharmaceuticals manufacturing is expected to rebound with 5.2 percent growth in 2024. 16 McKinsey analysis in partnership with Oxford Economics.

Healthcare demand could grow, although the quality of care may be strained as the health worker shortage is projected to increase over the next five years. 17 McKinsey analysis. The supply-and-demand gap in nursing alone is forecast to reach a shortage of approximately 90,000 nurses by 2028. 18 McKinsey analysis. Another compounding factor straining healthcare is the higher than anticipated benefit utilization and rising healthcare costs, which, while helping to meet people's healthcare budgets, may continue to drive down profitability for health insurers.

Meanwhile, pharmaceutical companies are feeling varying effects of people becoming increasingly health conscious. Consumers are using more over the counter (OTC) medication and placing more beneficial value on organic health products, such as vitamins and supplements made from natural ingredients, which could impact demand for prescription drugs. 19 “Consumer health in the Philippines 2023,” Euromonitor, October 2023.

Businesses operating in this field may end up benefiting from universal healthcare policies. If initiatives are implemented that integrate healthcare systems, rationalize copayments, attract and retain talent, and incentivize investments, they could potentially help to strengthen healthcare provision and quality.

Businesses may also need to navigate an increasingly complex landscape of diverse health needs, digitization, and price controls. Digital and data transformations are being seen to facilitate improvements in healthcare delivery and access, with leading digital health apps getting more than one million downloads. 20 Google Play Store, September 27, 2023. Digitization may create an opportunity to develop healthcare ecosystems that unify touchpoints along the patient journey and provide offline-to-online care, as well as potentially realizing cost efficiencies.

Consumer and retail

Growth in the retail and wholesale trade and consumer goods sectors is projected to remain stable in 2024, at 4 percent and 5 percent, respectively.

Inflation, however, continues to put consumers under pressure. While inflation rates may fall—predicted to reach 4 percent in 2024—commodity prices may still remain elevated in the near term, a top concern for Filipinos. 21 “IMF raises Philippine growth forecast,” July 26, 2023; “Nomura downgrades Philippines 2024 growth forecast,” September 11, 2023. In response to challenging economic conditions, 92 percent of consumers have changed their shopping behaviors, and approximately 50 percent indicate that they are switching brands or retail providers in seek of promotions and better prices. 22 “Philippines consumer pulse survey, 2023,” McKinsey, November 2023.

Online shopping has become entrenched in Filipino consumers, as they find that they get access to a wider range of products, can compare prices more easily, and can shop with more convenience. For example, a McKinsey Philippines consumer sentiment survey in 2023 found that 80 percent of respondents, on average, use online and omnichannel to purchase footwear, toys, baby supplies, apparel, and accessories. To capture the opportunity that this shift in Filipino consumer preferences brings and to unlock growth in this sector, retail organizations could turn to omnichannel strategies to seamlessly integrate online and offline channels. Businesses may need to explore investments that increase resilience across the supply chain, alongside researching and developing new products that serve emerging consumer preferences, such as that for natural ingredients and sustainable sources.


Manufacturing is a key contributor to the Philippine economy, contributing approximately 19 percent of GDP in 2022, employing about 7 percent of the country’s labor force, and growing in line with GDP at approximately 6 percent between 2023 and 2024. 23 McKinsey analysis based on input from industry experts.

Some changes could be seen in 2024 that might affect the sector moving forward. The focus toward building resilient supply chains and increasing self-sufficiency is growing. The Philippines also is likely to benefit from increasing regional trade, as well as the emerging trend of nearshoring or onshoring as countries seek to make their supply chains more resilient. With semiconductors driving approximately 45 percent of Philippine exports, the transfer of knowledge and technology, as well as the development of STEM capabilities, could help attract investments into the sector and increase the relevance of the country as a manufacturing hub. 24 McKinsey analysis based on input from industry experts.

To secure growth, public and private sector support could bolster investments in R&D and upskill the labor force. In addition, strategies to attract investment may be integral to the further development of supply chain infrastructure and manufacturing bases. Government programs to enable digital transformation and R&D, along with a strategic approach to upskilling the labor force, could help boost industry innovation in line with Industry 4.0 demand. 25 Industry 4.0 is also referred to as the Fourth Industrial Revolution. Priority products to which manufacturing industries could pivot include more complex, higher value chain electronic components in the semiconductor segment; generic OTC drugs and nature-based pharmaceuticals in the pharmaceutical sector; and, for green industries, products such as EVs, batteries, solar panels, and biomass production.

Information technology business process outsourcing

The information technology business process outsourcing (IT-BPO) sector is on track to reach its long-term targets, with $38 billion in forecast revenues in 2024. 26 Khriscielle Yalao, “WHF flexibility key to achieving growth targets—IBPAP,” Manila Bulletin , January 23, 2024. Emerging innovations in service delivery and work models are being observed, which could drive further growth in the sector.

The industry continues to outperform headcount and revenue targets, shaping its position as a country leader for employment and services. 27 McKinsey analysis based in input from industry experts. Demand from global companies for offshoring is expected to increase, due to cost containment strategies and preference for Philippine IT-BPO providers. New work setups continue to emerge, ranging from remote-first to office-first, which could translate to potential net benefits. These include a 10 to 30 percent increase in employee retention; a three- to four-hour reduction in commute times; an increase in enabled talent of 350,000; and a potential reduction in greenhouse gas emissions of 1.4 to 1.5 million tons of CO 2 per year. 28 McKinsey analysis based in input from industry experts. It is becoming increasingly more important that the IT-BPO sector adapts to new technologies as businesses begin to harness automation and generative AI (gen AI) to unlock productivity.

Talent and technology are clear areas where growth in this sector can be unlocked. The growing complexity of offshoring requirements necessitates building a proper talent hub to help bridge employee gaps and better match local talent to employers’ needs. Businesses in the industry could explore developing facilities and digital infrastructure to enable industry expansion outside the metros, especially in future “digital cities” nationwide. Introducing new service areas could capture latent demand from existing clients with evolving needs as well as unserved clients. BPO centers could explore the potential of offering higher-value services by cultivating technology-focused capabilities, such as using gen AI to unlock revenue, deliver sales excellence, and reduce general administrative costs.


The Philippines is considered to be the fourth most vulnerable country to climate change in the world as, due to its geographic location, the country has a higher risk of exposure to natural disasters, such as rising sea levels. 29 “The Philippines has been ranked the fourth most vulnerable country to climate change,” Global Climate Risk Index, January 2021. Approximately $3.2 billion, on average, in economic loss could occur annually because of natural disasters over the next five decades, translating to up to 7 to 8 percent of the country’s nominal GDP. 30 “The Philippines has been ranked the fourth most vulnerable country to climate change,” Global Climate Risk Index, January 2021.

The Philippines could capitalize on five green growth opportunities to operate in global value chains and catalyze growth for the nation:

  • Renewable energy: The country could aim to generate 50 percent of its energy from renewables by 2040, building on its high renewable energy potential and the declining cost of producing renewable energy.
  • Solar photovoltaic (PV) manufacturing: More than a twofold increase in annual output from 2023 to 2030 could be achieved, enabled by lower production costs.
  • Battery production: The Philippines could aim for a $1.5 billion domestic market by 2030, capitalizing on its vast nickel reserves (the second largest globally). 31 “MineSpans,” McKinsey, November 2023.
  • Electric mobility: Electric vehicles could account for 15 percent of the country’s vehicle sales by 2030 (from less than 1 percent currently), driven by incentives, local distribution, and charging infrastructure. 32 McKinsey analysis based on input from industry experts.
  • Nature-based solutions: The country’s largely untapped total abatement potential could reach up to 200 to 300 metric tons of CO 2 , enabled by its biodiversity and strong demand.

The Philippine economy: Three scenarios for growth

Having grown faster than other economies in Southeast Asia in 2023 to end the year with 5.6 percent growth, the Philippines can expect a similarly healthy growth outlook for 2024. Based on our analysis, there are three potential scenarios for the country’s growth. 33 McKinsey analysis in partnership with Oxford Economics.

Slower growth: The first scenario projects GDP growth of 4.8 percent if there are challenging conditions—such as declining trade and accelerated inflation—which could keep key policy rates high at about 6.5 percent and dampen private consumption, leading to slower long-term growth.

Soft landing: The second scenario projects GDP growth of 5.2 percent if inflation moderates and global conditions turn out to be largely favorable due to a stable investment environment and regional trade demand.

Accelerated growth: In the third scenario, GDP growth is projected to reach 6.1 percent if inflation slows and public policies accommodate aspects such as loosening key policy rates and offering incentive programs to boost productivity.

Focusing on factors that could unlock growth in its seven critical sectors and themes, while adapting to the macro-economic scenario that plays out, would allow the Philippines to materialize its growth potential in 2024 and take steps towards achieving longer-term, sustainable economic growth.

Jon Canto is a partner in McKinsey’s Manila office, where Frauke Renz is an associate partner, and Vicah Villanueva is a consultant.

The authors wish to thank Charlene Chua, Charlie del Rosario, Ryan delos Reyes, Debadrita Dhara, Evelyn C. Fong, Krzysztof Kwiatkowski, Frances Lee, Aaron Ong, and Liane Tan for their contributions to this article.

Explore a career with us

Related articles.

Philippines Growth Dialogues

The Philippines Growth Dialogues

plane flying over Philippines - line drawing

What does 2023 hold for the Philippines’ economy?

Close-up of woman's hand typing on a smartphone in the city in front of cars at beautiful sunset

On the verge of a digital banking revolution in the Philippines


  1. 10 Applications of Big Data in Manufacturing

    case study big data analytics in manufacturing

  2. Big Data Analytics Trends In Manufacturing Industry

    case study big data analytics in manufacturing

  3. Ten Ways Big Data Is Revolutionizing Manufacturing

    case study big data analytics in manufacturing

  4. IBM Big Data & Analytics and Manufacturing

    case study big data analytics in manufacturing

  5. Manufacturing Business Intelligence & Big Data Analytics Solution

    case study big data analytics in manufacturing

  6. 3 Types of Data Analytics that Boost Manufacturing

    case study big data analytics in manufacturing


  1. Case Study: Big Data Analytics at FlixBus



  4. Introduction to Data Analytics Lec 1

  5. Big data research Assingment-4



  1. Big Data Analytics for Smart Manufacturing: Case Studies in ...

    Smart manufacturing (SM) is a term generally applied to the improvement in manufacturing operations through integration of systems, linking of physical and cyber capabilities, and taking advantage of information including leveraging the big data evolution. SM adoption has been occurring unevenly across industries, thus there is an opportunity to look to other industries to determine solution ...

  2. Understanding Big Data Analytics for Manufacturing ...

    A big data analytics platform for smart factories in small and medium-sized manufacturing enterprises: An empirical case study of a die casting factory International Journal of Precision Engineering and Manufacturing , 18 ( 10 ) ( 2017 ) , pp. 1353 - 1361

  3. 14 Case Studies of Manufacturing Analytics in 2024

    14 Case Studies of Manufacturing Analytics in 2024. Manufacturing is one of the top 3 industries which account for the biggest share of the big data and analytics revenues worldwide. Manufacturing analytics have numerous use cases which enable businesses to predict machinery's future use, prevent failures, forecast maintenance requirements ...

  4. Big data analytics for intelligent manufacturing systems: A review

    A bibliometric analysis was conducted with published data from 2011 to 2020 regarding intelligent manufacturing driven by big data gathered from the Web of Science database (as shown in Fig. 1), which shows an almost steady increase in papers on this topic. Fig. 1 (a) shows the number of published articles about intelligent manufacturing from 2011 to 2020.

  5. Full article: Advancing manufacturing systems with big-data analytics

    In a case of big-data analytics, unlike more conventional data analytics, the choice of technology and storage and management techniques often strongly depends on the subsequently used data-analysis methods, and on the properties of the data under consideration. ... "Big Data in Manufacturing: A Systematic Mapping Study." Journal of Big ...

  6. Understanding Big Data Analytics for Manufacturing ...

    Big-data analytics capability (BDAC) is crucial for the value creation process and collaboration innovation of manufacturing enterprises. Based on the knowledge-based view, this study aims to explore the relationship between BDAC, the value creation process (collaboration breadth and collaboration depth), and collaboration innovation quality while considering the contingency of technology risk.

  7. Top 10 Manufacturing Analytics Use Cases in 2023

    IDC estimates that the global big data analytics market revenue would've reached ~$274B by 2022. This would have made manufacturing as one of the top 3 industries with largest analytics growth. Manufacturing analytics is one of the critical steps for manufacturing digital transformation required for Industry 4.0, which aims to: . Automate traditional manufacturing processes

  8. PDF Big Data Analytics for Smart Manufacturing: Case Studies in

    Big Data Analytics for Smart Manufacturing: Case Studies in Semiconductor Manufacturing James Moyne * and Jimmy Iskandar Applied Materials, Applied Global Services, 363 Robyn Drive, Canton, MI 48187, USA; [email protected] * Correspondence: [email protected]; Tel.: +1-734-516-5572 Received: 6 June 2017; Accepted: 4 July 2017; Published: 12 ...

  9. How big data can improve manufacturing

    The big data era has only just emerged, but the practice of advanced analytics is grounded in years of mathematical research and scientific application. It can be a critical tool for realizing improvements in yield, particularly in any manufacturing environment in which process complexity, process variability, and capacity restraints are present.

  10. Data Analytics for Smart Manufacturing: A Case Study

    analytics based on a real world case study. These. concepts include data understanding, data prepara- ... there is an increasing need of handling big manufacturing data characterized by high ...

  11. Big Data Analytics in the Manufacturing Sector: Guidelines ...

    Alignment between business strategy and Big Data solutions is a critical factor for achieving value through Big Data [].Manufacturers must understand how the adoption of Big Data technologies [] is related to their business objectives in order to identify the right datasets and increase the value of the analytics results.Therefore tailoring Big Data requirements to the business needs is the ...

  12. Data Analytics for Manufacturing: the Tesla's Case Study (Part 1)

    And Elon Musk is aiming to deliver 500,000 vehicles by 2018 and 1,000,000 by 2020. Last December, the city of Fremont, California, approved Tesla's plans to double the size of its factory there. There will be an additional 420,000 square meters of manufacturing space. And the number of workers is expected to increase from 6,000 to 9,000.

  13. Big Data Analytics for Smart Manufacturing: Case Studies in

    In the future, an improved big data environment incorporating smart manufacturing concepts such as digital twin will further enable analytics; however, it is anticipated that the need for incorporating subject matter expertise in solution design will remain. Smart manufacturing (SM) is a term generally applied to the improvement in manufacturing operations through integration of systems ...

  14. Model-based Big Data Analytics-as-a-Service framework in smart

    Section snippets Big data analytics for smart manufacturing. The increasing complexity of manufacturing processes, which are highly dependant on demand trends, and the exponential growth in the amount of data associated with them have given rise to some major challenges with respect to data acquisition, process monitoring and anomaly detection [19].

  15. 14 Fascinating Case Studies of Manufacturing Analytics in Action

    The manufacturing sector is undergoing a technology-fueled transformation. According to IDC, manufacturing accounted for 11% of the $215 billion spent on big data and analytics solutions in 2022. With the proliferation of industrial internet of things (IIoT) and advances in artificial intelligence (AI), manufacturers now have access to a wealth ...

  16. From Concept to Use Cases: Big Data Analytics in Manufacturing

    Big data analytics in manufacturing is all you need to improve your business's efficiency, quality, and productivity in today's data-driven industry. It helps you transform your business data into actionable analytics to make informed decisions on business processes and operations. "Data is the new science. Big data holds the answers.".

  17. Data Analytics in Manufacturing Case Study

    AI-Driven Quality and Safety Solutions: We help manufacturers harness the power of AI-driven analytics to revolutionize quality control and safety in manufacturing. Companies can leverage advanced algorithms to detect anomalies, enhance defect detection, and ensure a safe working environment, driving unparalleled quality and safety standards.

  18. PDF Data Analytics for Smart Manufacturing: A Case Study

    Data Analytics for Smart Manufacturing: A Case Study. Nadeem Iftikhar1, Thorkil Baattrup-Andersen2, Finn Ebertsen Nordbjerg1, Eugen Bobolea1. and Paul-Bogdan Radu1. 1University College of Northern Denmark, Aalborg 9200, Denmark. 2Dolle A/S, Frøstrup 7741, Denmark Keywords: Industry 4.0, Data Analytics, Smart Manufacturing, Logistic Regression ...

  19. Data Analytics for Smart Manufacturing: A Case Study

    The objective of this paper is to propose data analytic techniques to analyze manufacturing data that will provide both descriptive and predictive analysis and will help the companies to improve operational efficiency and achieve competitive benefits. Due to the emergence of the fourth industrial revolution, manufacturing business all over the world is changing dramatically; it needs enhanced ...

  20. Understanding Big Data Analytics for Manufacturing Processes: Insights

    @article{Belhadi2019UnderstandingBD, title={Understanding Big Data Analytics for Manufacturing Processes: Insights from Literature Review and Multiple Case Studies}, author={Amine Belhadi and Karim Zkik and Anass Cherrafi and Yusof Bin Mohd Sha'ri and Said El Fezazi}, journal={Comput. Ind.

  21. Big Data Analytics for Predictive Manufacturing Control

    Big Data Analytics for Predictive Manufacturing Control - A Case Study from Process Industry ... However, without dedicated approaches of big data analytics, the sample company cannot utilize the potential of already available data for a proactive process control. Hence, the article forms a working and discussion basis for further research in ...

  22. Big data analytics for intelligent manufacturing systems: A review

    With the development of artificial intelligence, big data analytics (BDA) have been greatly improved to effectively mine both structured and unstructured industrial data in intelligent manufacturing, which has become a new research hotspot [4]. Continuous learning from big data of manufacturing system enables the system to be self-learning ...

  23. Data Science Supporting Lean Production: Evidence from Manufacturing

    In this study, multiple case studies were conducted involving the Italian manufacturing sector to collect evidence of the application of data science to support lean production and to understand it. The results provide empirical proof of the link and examples of a variety of data science techniques and tools that can be combined to support lean ...

  24. Model-based Big Data Analytics-as-a-Service framework in smart

    The adopted Model-based Big Data Analytics-as-a-Service framework and the configured cloud-based Big Data platform (to run the entire BDA pipeline in the aeronautical manufacturing case study) overcame the major challenges that have, so far, prevented many companies from reaping the full benefits of Big Data analytics.

  25. The Philippines economy in 2024

    [email protected]. Inflation rates are expected to temper between 3.2 and 3.6 percent in 2024 after ending 2023 at 6.0 percent, above the 2.0 to 4.0 percent target range set by the government. 5. For the purposes of this article, most of the statistics used for our analysis have come from a common thread of sources.