Scholarlink

In recent years, the global Supply Chain (SC) has encountered numerous unexpected obstacles and risks. Consequently, manufacturing plants and delivery networks were facing serious problems due to these unexpected events. Technological advances indicate that Machine Learning (ML) and associated algorithms have changed the way to solve these problems and improve the overall resilience, agility, efficiency of SC operations, adaptability and responsiveness of SC Management (SCM) systems. This paper employs a Systematic Literature Review Method (SLRM) to explore the use of ML in SCM, analyzing research from 2014 to 2024 to examine how techniques like predictive modeling, optimization algorithms, and self-decision making (i.e., systems capable of making autonomous decisions based on real-time data without human intervention) improve SC operations. The goal is to provide practitioners and researchers with insights into ML's potential to increase efficiency, reduce risk, and drive innovation in areas such as customer planning, procurement, logistics, and order execution. Through this comprehensive review, the study aims to equip SC professionals with tools to develop effective ML applications and address critical issues within SC systems.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The Transformative Role of ML Algorithms in Supply Chain Management: A Systematic Literature Review

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Khaoula Elkabtane,
  • Touria Benazzouz,
  • Samya Dahbi,
  • Khalid Auhmani

摘要

In recent years, the global Supply Chain (SC) has encountered numerous unexpected obstacles and risks. Consequently, manufacturing plants and delivery networks were facing serious problems due to these unexpected events. Technological advances indicate that Machine Learning (ML) and associated algorithms have changed the way to solve these problems and improve the overall resilience, agility, efficiency of SC operations, adaptability and responsiveness of SC Management (SCM) systems. This paper employs a Systematic Literature Review Method (SLRM) to explore the use of ML in SCM, analyzing research from 2014 to 2024 to examine how techniques like predictive modeling, optimization algorithms, and self-decision making (i.e., systems capable of making autonomous decisions based on real-time data without human intervention) improve SC operations. The goal is to provide practitioners and researchers with insights into ML's potential to increase efficiency, reduce risk, and drive innovation in areas such as customer planning, procurement, logistics, and order execution. Through this comprehensive review, the study aims to equip SC professionals with tools to develop effective ML applications and address critical issues within SC systems.