Data Science Applications in Supply Chain Management Decision-making

Research Article
Open access

Data Science Applications in Supply Chain Management Decision-making

Published on 26 June 2024 | https://doi.org/10.54254/2754-1169/108/20241920
Zean Gong *,1
  • 1 Simra Academy Private School, Scarborough, Canada    

* Author to whom correspondence should be addressed.

Gong,Z. (2024). Data Science Applications in Supply Chain Management Decision-making. Advances in Economics, Management and Political Sciences,108,36-43.
Export citation
AEMPS Vol.108
ISSN (Print): 2754-1177
ISBN (Print): 978-1-83558-545-0
ISSN (Online): 2754-1169
ISBN (Online): 978-1-83558-546-7
Download Cover Download Volume

Abstract

This research views data science as the basis of the decision-making process at SCM. Tough international trade environment characterized by complex supply chain and inventory issues as well as unpredictable demand for goods necessitates powerful analytics tools. Using the latest technologies - machine learning, predictive analytics, and big data - data science generates data-driven decisions for more accurate, efficient, and prompt SCM decision-making. The study intends to study the current trends and evaluate the influence of data science in SCM decision-making processes. It also delves into the difficulties and advantages with the utilization of data science during these procedures. This study uses a synthesis approach by systematically going through a literature review to gather data from different academic journals and industry publications. According to the results of the thematic analysis, the themes will emerge, so the whole complexity and depth of data science applications in SCM will be properly revealed. Data science changes the business decision-making in a way that was impossible before with the advent of new information from the huge and complex data sources. Data analytics not only smoothens but also upgrades long-term trend forecasting and market readiness in SCM. Furthermore, the paper emphasizes the influence of the Internet of Things (IoT) and industry 4.0 technologies of SCM with an accent on how they are associated to increase efficiency and sustainability in the operations.

Keywords

Data Science in SCM, Predictive Analytics, Operational Efficiency

1. Introduction

1.1. Background

The current global business environment is fast changing with data science being at the heart of supply chain management. It has brought in a new age of smart decision-making. More and more companies are experiencing problems with logistics, inventory management, and demand forecasting, too. In this regard, robust analytical frameworks becomes necessary. Data science is done by applying some of the advanced techniques that include machine learning, predictive analytics and big data technologies thus increasing the level of accuracy, efficiency and responsiveness in SCM [1].

Data science is redesigning the core of traditional business decision-making processes through providing new insights from large and complex datasets that SCM usually requires. The discovery of this kind of insights convert raw data into actionable intelligence, which allows making effective decisions that give the operational efficiency and competitive edge. The role of data science in SCM is becoming more and more crucial as it allows businesses to overcome the conventional difficulties including poor operational efficiency, wrong demand estimation, and unproductive resource allocation.

Application of sophisticated analytics allows organizations to synchronize and boost their supply chain response. This adjustment goes a long way to meeting competitiveness in a changing market and the ever-evolving consumer need in an effective way. The application of data science in supply chain processes apart from that smoothens processes also depends on data advanced analytics to forecast trends and prepare for different market situation [2].

This metamorphosis in data science in SCM is pivotal for building more intelligent supply chains that can self-adjust to any change in the supply chain environment hence resilience amid uncertainties will be ensured.

1.2. Objectives

a. To analyse the present trends of the data science application in the field of supply chain management.

b. To evaluate the influence data science has on decision-making processes in supply chain management.

c. To examine the problems and advantages with the merging of data science into supply chain decision-making.

1.3. Research Questions

a. What are the current trends in data science application within supply chain management?

b. How does data science affect the decision-making process in supply chain management?

c. What are the challenges and opportunities of data science in enhancing supply chain decision making?

2. Literature Review

2.1. Data Science in Supply Chain Management

Data Science in SCM is based on various tools, methods, and models that are used to solve problems that cannot be handled by the conventional approaches adequately. The association of data science and SCM can be illustrated with statistical analysis, predictive modelling, machine learning algorithms, and big data analytics, which are helpful in optimizing and synchronizing the business decision process throughout the supply chain. As per the opinion of Chauhan and Singh [3] these tools enable forecasting, automating processes and hence, increasing the efficiency of the organization. The infusion of data science into SCM not only amplifies the process visibility but also helps in taking wise strategic decisions too.

2.2. Current Trends and Applications

The new perspective suggests that the deployment of data science models into demand forecasting, inventory optimization, logistics management, and risk assessment is now a critical element in SCM. On the other hand, Zhou and Wang [4] raise that machine learning models are currently applied by various organizations to forecast accurately demand patterns and then to have improved stock management so as to end up with less waste. In inventory optimization, algorithms are created to govern stock levels simultaneously across channels which decrease the inventories cost and availability of the product to the end user [5].

In logistics management, advanced analytics are employed to route optimization and enhance delivery efficiency by predicting possible delays as well as dynamically adjusting routes in real-time [6]. Data science is now employed in risk assessment in supply chains; predictive models assist in forecasting possible disruptions and formulating measures to mitigate vulnerability [7].

2.3. Impact on Decision-making

Data science has tremendous impact on decision-making processes of supply chain management. As postulated by Lee and Chien, data-driven decision-making helps organizations in minimizing operational costs and improving service level by facilitating more accurate predictions and useful resource allocation. In addition, real-time data analysis can help organizations to react faster to market changes and improve resiliency. According to them, data science enables better synchronization among the various supply chain stages, which reduces response time and eliminates bottlenecks.

2.4. Challenges and Opportunities

Although the implementation of data science in SCM provides multiple benefits, it also implies big challenges. One of the central issues pointed out in literature is data quality and quantity. As highlighted by Zhou and Wang [4], the data science initiatives' effectiveness largely stems from the accessibility of high-quality relevant data. Weak or fluctuating data may result in the wrong results or costly decisions.

Safety and security are other vital additionally issues, particularly the sensitive nature of supply chain data, which often includes data from different stakeholders. This information must be guarded against breaches and compliance with the global data protection laws must be done.

On the opportunity side, the use of data science to manage supply chain is not going to reach its peak. Recent novelties in artificial intelligence and machine learning promise further improvements in efficiency and performance. For example, AI can eliminate human errors in making automated decisions and accelerate the processes. Moreover, the IoT devices can also be integrated with data science for the tracking of goods and assets, which will increase the accuracy of data for analysis.

2.5. Knowledge Gap

Data science in supply chain management has had a lot of research despite the gap of understanding in long-term strategic effects and the scalability of data-driven solutions within diverse industries. Moreover, there are almost no studies out there on the overall impact of data integration on supply chain sustainability.

3. Methodology

3.1. Research Design

This study uses a qualitative research design and its primary approach is a systematic literature review to explore data science applications in supply chain management. The qualitative approach is selected for its strength in understandably and broadly exploring the currently available theories and models, and for its ability to understand the depth and complexity of how data science is being integrated into the decision-making in the supply chains. On contrast with quantitative methods which try to measure the problems through numbers and mixed methods that combine both qualitative and quantitative approaches, the qualitative method explores in detail the intricacies and themes that lie in literature. This approach is especially suited to the goals of looking at trends, measuring impacts, and investigating the opportunities and challenges of data science in a SCM system, where grasping the context and larger implications is paramount.

3.2. Data Collection

For this research, data will be collected via systematic literature review that is a structured search in academic journals, conference proceedings, and industry reports. Through this, the entire field of data science in supply chain management is covered in a systematic way. The primary databases such as PubMed, Science Direct, and JSTOR will be the sources of information. The search terms will be “data science and supply chain management”, “predictive analytics in SCM”, “AI in logistics” and “big data applications in SCM.” The literature will be screened according to the following criteria: works published in the last ten years to ensure the relevance and currency of the data. Such a methodical way allows identifying the major research and trends, and the base for the analysis is formed.

3.3. Data Analysis

The collected data will be analysed using thematic analysis - an approach familiar for qualitative research - which enables one to identify, analyse and report patterns (themes) within the data. It will include the method of reading and re-reading the literature to be able to grasp the depth and width of the subject. The primary codes will be constituted by picking out thoughts and main themes from the texts. The codes will be then compiled into possible themes and inspected to make sure that they form a logical structure and are relevant to the research questions. This thematic approach to data analysis satisfies the complexities of how data science makes the decision-making in SCM domain, identifies the emerging trends and understand the problems and chances of incorporating of advanced data analytics into SCM processes.

3.4. Ethical Considerations

The ethical issues in this study relate to the appropriate use and mentioning the collected data. As this research paper hinges on a systematic literature review, it is necessary to make sure that all sources are properly referenced and that the data is acquired in a public and ethical manner. Ethical compliance will consist of compliance with intellectual property rights, obtaining permissions for the use of protected content where necessary and keeping the confidentiality and anonymity of study contributions if applicable. Furthermore, the review process will take into account any biases in selecting and perceiving information to provide the most fair and balanced assessment. Strategies to deal with these ethical issues could involve a thorough peer review process of the methodology and findings, preserving a transparent audit trail of the data collection and analysis decisions and making sure that a critical appraisal of the literature is done and publicly discussed.

4. Results and Discussion

4.1. Results

Table 1: Results of the themes after the thematic analysis.

Theme Subthemes Codes Paper Reference
Big Data Analytics Predictive Analytics Demand forecasting Koot et al., 2021
Risk assessment Sarker, 2021
Inventory management Maheshwari et al., 2021
Decision Support Systems Optimization models Jha et al., 2020
Real-time data processing Lee and Chien, 2022
Machine Learning Regression analysis Qiu et al., 2020
Classification methods Qiu et al., 2020
Clustering techniques Sarker, 2021
Data-Driven Strategies Strategic decision making Chauhan and Singh, 2020
Data integration Koot et al., 2021
Internet of Things (IoT) IoT Devices Sensors and tracking Koot et al., 2021
Connectivity and networks Sarker, 2021
IoT in Operations Real-time monitoring Koot et al., 2021
Automation in warehousing Chauhan and Singh, 2020
IoT Data Management Data collection and storage Sarker, 2021
Data privacy and security Lee and Chien, 2022
Sustainable Practices Circular Economy Recycling and reuse Wang et al., 2020
Sustainability metrics Mageto, 2021
Green Supply Chain Carbon footprint reduction Mageto, 2021
Eco-friendly materials Wang et al., 2020
Regulatory Compliance Environmental regulations Mageto, 2021
Compliance monitoring Lee and Chien, 2022
Industry 4.0 Technologies Advanced Robotics Robotic process automation Chauhan and Singh, 2020
Machine-to-machine interaction Lee and Chien, 2022
Smart Factories Digital twins Chauhan and Singh, 2020
Predictive maintenance Lee and Chien, 2022
Blockchain Technology Transaction transparency Wang et al., 2020
Smart contracts Wang et al., 2020
Decision Making Strategic Decisions Long-term planning Maheshwari et al., 2021
Competitive strategy Chauhan and Singh, 2020
Operational Decisions Logistics optimization Jha et al., 2020
Production scheduling Lee and Chien, 2022
Tactical Decisions Resource allocation Maheshwari et al., 2021
Supplier selection Jha et al., 2020

The thematic table for the systematic literature review on Data Science Applications in Supply Chain Management Decision-Making organizes key research findings into five main themes: Data analytics of Big Data, the Internet of Things (IoT), sustainable practices, Industry 4.0 technologies, and decision-making. Each theme is subsequently fragmented into subthemes that deal with specific issues such as predictive analytics, Internet of Things devices, circular economy methods, advanced robotics and various levels of making decisions. The codes under these themes comprise of many details and topics such as demand forecasting, real-time monitoring, sustainability metrics, digital twins and long-term strategic planning. With machine learning, block chain, and IoT the table shows how supply chain operations can support decision accuracy, operational efficiency, and sustainability. The structured analysis does not only cover the innovations in the supply chain technology aspect but also emphasizes the implications of them and the potential.

4.2. Discussion

4.2.1. Big Data Analytics in Supply Chain Management

Big Data Analytics is a critical source of information that assist in reshaping supply chains by making it possible for decision-makers to make more informed decisions that lead to higher operational efficiency. With the help of predictive analytics, organizations can forecast future demands, recognize supply chain barriers and streamline stock levels. Koot et al. [2] argue that the broad analysis of enormous datasets from multiple sources enhances prediction precision, and risk assessments. Sarker [1] additionally points out that regression analysis and classifier techniques are some of the machine learning methods applied to the steering processes, thus making them evidence-based and less prone to human errors.

Decision support systems, such as those mentioned by Jha et al. [8], utilize big data to provide real-time feedback and implement prescriptive analytics, allowing companies to deal efficiently with dynamic market conditions. Lee and Chien [7] identify the danger spots of production practices and propose that sensitive data management methods can lower the risks in data science tools. With the help of data-driven strategies as discussed by Chauhan and Singh [3], it becomes easy to have a synchronic approach of supply chain operations with the business goals.

4.2.2. Internet of Things (IoT) Integration

IoT is the transformative technology in Supply Chain Management, as it improves connectivity and visibility within the supply chain network. IoT devices like sensors and RFID tags are involved in data transmission all the time, assisting in the real-time tracking of goods, which in turn leads to improved inventory management and reduction of losses because of the overstocking and stock outs [2]. By IoT, connectivity and networks information exchange among supply chain segments would be smooth and the operation of the various segments would become synchronized as analysed by Sarker [1].

In addition, real-time monitoring enabled by IoT makes managerial decisions easier. The managers can take care of the issues before they get out of hand and thus they can avoid the inefficiency of the operations [2]. On the other hand, with the help of IoT the automation within the warehouses and the manufacturing plants is very much vital to cut down the labour costs and boost the productivity [3]. Data management issues, such as data confidentiality and security, are a major problem with the introduction of IoT systems to industrial processes, and it is recommended to have a reliable strategy to deal with this matter, as proposed by Lee et al. [7].

4.2.3. Sustainable Practices in Supply Chain

Eco-friendly practices are progressively vital for today's supply chains and even more so toward Industry 4.0. The integration of technology including IoT and big data analytics has shaped the direction to more sustainable and circular supply chains, where resource efficiency and waste reduction are in the focus. Wang et al. [6] look at the block chain-supported frameworks that can provide transparency and traceability in circular supply chains and allow sustainability in fast fashion industries.

Mageto [9] highlights big data analytics in sustainable supply chain management by showing how data can be used to monitor sustainability metrics and thus improve environmental performance across manufacturing environments. This is, therefore, both a legal necessity and a consumer demand. The part that compliance with regulations plays in making the operations sustainable is also important, as businesses must implement the growing number of environmental regulations [7].

4.2.4. Industry 4.0 Technologies

The Industry 4.0, which is the fourth industrial revolution, incorporates technologies like robots, artificial intelligence, and block chain into the manufacturing and supply chain sectors. These technologies are responsible for the major gains in operation efficiency and precision Robotics can be seen as an instance of advanced robotics that automate warehouses, reduce error rate and accelerate operations [3]). Digital twins, another cutting-edge technology, is often referred to as the virtual replica of physical systems that provide simulations and analysis for predictive maintenance and operational planning [7].

Block chain technology comes with added elements of transparency and security in supply chain transactions. All the parties can access immutable records of the transactions and this is particularly useful in complex, multi-tier supply chains [6]. This transparency counts for the establishing of trust and for verifying contractual obligations without the involvement of the traditional, often complicated, verification procedures.

4.2.5. Decision Making Enhancement

One of the most direct impacts technology has on the supply chain management processes is data science, which improves the decision-making process. Uncertainties in planning and various strategies could now be reduced by data analytics that generate deep understanding of market trends and consumer behaviour [10]. In IoT and big data, operational judgements are equally improved, not only in logistics management, but also in production planning and advancement [8].

At the strategic level, supply chain management can help to allocate resources more precisely and to optimize supplier selection by using performance data and predictive analytics thus reducing risks and enhancing the overall resilience of the supply chain. This makes not only the financial performance of companies but also the overall environmental and economic sustainability of whole industries better.

5. Conclusion

In conclusion, the combination of data science, IoT (Internet of Things), and Industry 4.0 technologies in logistics signifies a major step forward in terms of improvement of the operational effectiveness and the strategic and tactical decision making processes. According to the research findings of the recent studies, the modern technologies allow enterprises to react quickly and effectively to customer needs. Moreover, they help organizations to achieve regulatory requirements and environmental objectives with more process ease and accuracy.

Meanwhile, this tech-driven synergy in logistics not only streamlines the workflow but also introduces automation and data-driven insights at the next level. The capturing of real-time data through IoT devices along the supply chain, as well as the application of data science methodologies to these vast datasets, gives companies the capacity to foresee market trends and optimize routes, inventory, and downtime. However, Industry 4.0 welcomes in a new era of digital transformation via smart factories and interconnected machinery, which not only enhance productivity but also significantly cut down the operational costs.

The impact of supply chain management cannot be downplayed. These technologies will experience an increase in adoption, which will pave the way for global supply chain systems where innovation rates will be unprecedented. For this reason, the businesses that successfully apply data science, IoT, and Industry 4.0 will have an advantage over their competitors by implementing more adaptable, sustainable, and cost-effective supply chain strategies. Not only is the establishment of a new order of global logistics but also the alteration of industrial dynamics and customer satisfaction promised by this alignment with technological advancements.


References

[1]. Sarker, I.H. (2021) Data science and analytics: an overview from data-driven smart computing, decision-making and applications perspective. SN Computer Science, 2(5), p.377.

[2]. Koot, M., Mes, M.R. and Iacob, M.E. (2021) A systematic literature review of supply chain decision making supported by the Internet of Things and Big Data Analytics. Computers & industrial engineering, 154, p.107076.

[3]. Chauhan, C. and Singh, A. (2020) A review of Industry 4.0 in supply chain management studies. Journal of Manufacturing Technology Management, 31(5), pp.863-886.

[4]. Zhou, X., Wang, M. and Li, D. (2019) Bike-sharing or taxi? Modeling the choices of travel mode in Chicago using machine learning. Journal of transport geography, 79, p.102479.

[5]. Qiu, H., Luo, L., Su, Z., Zhou, L., Wang, L. and Chen, Y. (2020) Machine learning approaches to predict peak demand days of cardiovascular admissions considering environmental exposure. BMC medical informatics and decision making, 20, pp.1-11.

[6]. Wang, B., Luo, W., Zhang, A., Tian, Z. and Li, Z. (2020) Blockchain-enabled circular supply chain management: A system architecture for fast fashion. Computers in Industry, 123, p.103324.

[7]. Lee, C.Y. and Chien, C.F. (2022) Pitfalls and protocols of data science in manufacturing practice. Journal of Intelligent Manufacturing, 33(5), pp.1189-1207.

[8]. Jha, A.K., Agi, M.A. and Ngai, E.W. (2020) A note on big data analytics capability development in supply chain. Decision Support Systems, 138, p.113382.

[9]. Mageto, J. (2021) Big data analytics in sustainable supply chain management: A focus on manufacturing supply chains. Sustainability, 13(13), p.7101.

[10]. Maheshwari, S., Gautam, P. and Jaggi, C.K. (2021) Role of Big Data Analytics in supply chain management: current trends and future perspectives. International Journal of Production Research, 59(6), pp.1875-1900.


Cite this article

Gong,Z. (2024). Data Science Applications in Supply Chain Management Decision-making. Advances in Economics, Management and Political Sciences,108,36-43.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About volume

Volume title: Proceedings of the 3rd International Conference on Financial Technology and Business Analysis

ISBN:978-1-83558-545-0(Print) / 978-1-83558-546-7(Online)
Editor:Ursula Faura-Martínez
Conference website: https://2024.icftba.org/
Conference date: 4 December 2024
Series: Advances in Economics, Management and Political Sciences
Volume number: Vol.108
ISSN:2754-1169(Print) / 2754-1177(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).

References

[1]. Sarker, I.H. (2021) Data science and analytics: an overview from data-driven smart computing, decision-making and applications perspective. SN Computer Science, 2(5), p.377.

[2]. Koot, M., Mes, M.R. and Iacob, M.E. (2021) A systematic literature review of supply chain decision making supported by the Internet of Things and Big Data Analytics. Computers & industrial engineering, 154, p.107076.

[3]. Chauhan, C. and Singh, A. (2020) A review of Industry 4.0 in supply chain management studies. Journal of Manufacturing Technology Management, 31(5), pp.863-886.

[4]. Zhou, X., Wang, M. and Li, D. (2019) Bike-sharing or taxi? Modeling the choices of travel mode in Chicago using machine learning. Journal of transport geography, 79, p.102479.

[5]. Qiu, H., Luo, L., Su, Z., Zhou, L., Wang, L. and Chen, Y. (2020) Machine learning approaches to predict peak demand days of cardiovascular admissions considering environmental exposure. BMC medical informatics and decision making, 20, pp.1-11.

[6]. Wang, B., Luo, W., Zhang, A., Tian, Z. and Li, Z. (2020) Blockchain-enabled circular supply chain management: A system architecture for fast fashion. Computers in Industry, 123, p.103324.

[7]. Lee, C.Y. and Chien, C.F. (2022) Pitfalls and protocols of data science in manufacturing practice. Journal of Intelligent Manufacturing, 33(5), pp.1189-1207.

[8]. Jha, A.K., Agi, M.A. and Ngai, E.W. (2020) A note on big data analytics capability development in supply chain. Decision Support Systems, 138, p.113382.

[9]. Mageto, J. (2021) Big data analytics in sustainable supply chain management: A focus on manufacturing supply chains. Sustainability, 13(13), p.7101.

[10]. Maheshwari, S., Gautam, P. and Jaggi, C.K. (2021) Role of Big Data Analytics in supply chain management: current trends and future perspectives. International Journal of Production Research, 59(6), pp.1875-1900.