A Systematic Analysis on the Research Trends of Machine Learning in Supply Chain Management

Concerns about a lack of data have given way to concerns about an abundance of information needed for supply chain management (SCM) in today's multifaceted and constantly changing world. The quantity of data produced by each node in the supply chain has altered how SCM analysis works. The increase in data amount has decreased the usefulness and efficiency of earlier methods. Due of the shortcomings of traditional methodologies in evaluating and comprehending enormous amounts of data, researchers have created other ways that have a great capacity for doing so. This essay's main focus is on machine learning (ML) uses for supply chain management (SCM), one of the most well-liked artificial intelligence (AI) techniques. The primary goals of this article are to understand the significance of computational learning in categorising and decision-making challenges and to assess the applicability of ML techniques in various supply chain domains, such as demand projections, earnings administration, journey strategy, managing inventories, and the renewable economy.