Enhancing supply chain management with deep learning and machine learning techniques: A review

Abstract

Supply chain management (SCM) is crucial in establishing long-term partnerships that are pivotal for achieving sustained business success. Effective SCM demands rigorous criteria and decision-making processes, which significantly impact the overall outcomes. Recent studies highlight cloud-based market analysis as a valuable tool for assessing supply chain dynamics, offering insights into the benefits and challenges of SCM. The integration of deep learning (DL) and machine learning (ML) approaches in SCM presents transformative potential, enabling more efficient management of the supply chain. This paper identifies the contributions of DL and ML techniques in various aspects of SCM, including supplier selection, production, inventory control, transportation, demand and sales estimation, and others. The extensive review presented in this work delivers an in-depth examination of the integration of DL and ML with SCM, highlighting strategies for enhancing operational efficiency, addressing current limitations, and identifying future research opportunities. A comprehensive literature table consolidates existing research on enhancing SCM with ML and DL techniques, offering a precise overview of objectives, findings, and areas for improvement, and providing rapid insights into the evolving landscape of SCM.

Keywords

• Multi-criteria decision-making
• Deep learning
• Supply chain management
• Machine learning
• Supplier selection