TY - JOUR
T1 - Leveraging synthetic data to tackle machine learning challenges in supply chains
T2 - challenges, methods, applications, and research opportunities
AU - Long, Yunbo
AU - Kroeger, Sebastian
AU - Zaeh, Michael F.
AU - Brintrup, Alexandra
N1 - Publisher Copyright:
© 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
PY - 2025
Y1 - 2025
N2 - Machine learning (ML) has the potential to improve various supply chain management (SCM) tasks, namely demand forecasting, risk management, inventory management, production planning and control, supply network reconstruction, and distribution and logistics. However, the industrial application of ML in supply chains faces many challenges, particularly in data privacy and data scarcity. Synthetic data, which is artificially generated to mimic real-world data patterns, has shown promise in overcoming similar challenges in fields such as healthcare and finance. However, the application of synthetic data in the context of supply chains remains limited. This publication aims to analyze the challenges of machine learning operations (MLOps) for supply chain tasks and explain how synthetic data can address these challenges in a supply chain context. Moreover, the publication aims to identify suitable approaches to generate synthetic supply chain data. Based on the analysis, a research agenda is proposed as a guideline for future research activities to enable the use of synthetic data in the context of supply chains.
AB - Machine learning (ML) has the potential to improve various supply chain management (SCM) tasks, namely demand forecasting, risk management, inventory management, production planning and control, supply network reconstruction, and distribution and logistics. However, the industrial application of ML in supply chains faces many challenges, particularly in data privacy and data scarcity. Synthetic data, which is artificially generated to mimic real-world data patterns, has shown promise in overcoming similar challenges in fields such as healthcare and finance. However, the application of synthetic data in the context of supply chains remains limited. This publication aims to analyze the challenges of machine learning operations (MLOps) for supply chain tasks and explain how synthetic data can address these challenges in a supply chain context. Moreover, the publication aims to identify suitable approaches to generate synthetic supply chain data. Based on the analysis, a research agenda is proposed as a guideline for future research activities to enable the use of synthetic data in the context of supply chains.
KW - data generation
KW - generative AI
KW - Machine learning
KW - MLOps
KW - supply chain
KW - synthetic data
UR - http://www.scopus.com/inward/record.url?scp=85214388396&partnerID=8YFLogxK
U2 - 10.1080/00207543.2024.2447927
DO - 10.1080/00207543.2024.2447927
M3 - Article
AN - SCOPUS:85214388396
SN - 0020-7543
JO - International Journal of Production Research
JF - International Journal of Production Research
ER -