Machine Learning Applications in End-To-End Supply Chain Management: A Comprehensive Review

Machine Learning; Supply Chain Management; Procurement; Demand Forecasting; Production; Inventory Management; Warehousing; Transportation; Artificial Intelligence

Authors

Vol. 13 No. 06 (2025)
Engineering and Computer Science
June 5, 2025

Downloads

Machine Learning (ML) has emerged as a pivotal technology in Supply Chain Management (SCM), enabling data-driven optimizations in procurement, demand forecasting, production scheduling, inventory control, warehousing operations, and transportation routing. This paper presents a comprehensive academic review of ML applications across all major SCM functions. We integrate insights from over 50 peer-reviewed studies to examine how various ML techniques – from classical algorithms to deep learning – are employed to improve supplier selection, predict demand more accurately, optimize manufacturing processes, manage inventory levels, streamline warehouse management, and enhance transportation and distribution efficiency. The review discusses methodological approaches, highlights results such as improved forecast accuracy and cost reduction, and analyzes comparative performance of different ML methods. The paper also identifies current challenges (data quality, integration, model interpretability) and outlines future research directions, including the integration of ML with IoT and blockchain for end-to-end supply chain visibility, and the exploration of reinforcement learning and generative AI for decision automation.