Machine Learning Models for Optimizing Supply Chain Management
Sanabel Alkubaisi, Ali Fenjan, Talib A. Al-Sharify, Salsal Sadiq, Hussein Basim Furaijl, Saadaldeen Rashid Ahmed
Abstract
This study attempts to tackle the issue of supply chain management utilizing machine learning models. The major objective is to improve supply chain operations in terms of speed, quality, and dependability with the aid of advanced prediction models. Applying a variety of machine learning approaches, including regression models, neural networks, and ensemble models, the research investigates a huge dataset comprising supply chain variables, including demand estimates, inventory levels, and transportation data. Some of the study results imply that the usage of machine learning models is significantly more successful than traditional strategies in terms of prediction and resource utilization. Optimization approaches also enhance model performance and hence minimize the operating cost and improve the alignment to the supply chain objectives. It is observed that the inclusion of machine learning in SCM has substantial benefits and establishes the framework for additional study on the combination of methodologies, real-time data integration, and sustainability KPIs. Such developments are anticipated to boost creativity and improve decision making in the supply chain.