Abstract:

The use of machine learning in operations management provides opportunities to optimize SCM processes demand forecasting, inventory control, and SCM resource distribution accuracy and efficiency all improve. Most businesses struggle with operational expenses and missed opportunities because of broken systems for managing obsolete inventory, insufficient demand forecasting, and operational lags. These issues tend to deteriorate due to unrefined techniques that lag in sophisticated inventory maintenance. This model proposes a solution through careful application of ML techniques to predictive demand analysis within SCM under the framework of Machine Learning-based Demand Forecasting in Supply Chain Management (ML-DF-SCM). This model considers not only historical data, but also prevailing market trends, which allows for a dramatic improvement in the control of inventory levels, resource allocation, promptness of delivery, and other activities concerning optimization of the entire supply chain. Implementation results testify to improved accuracy of demand forecasts, lower overall operational costs in SC system functions, and increase in performance refinery in SC systems.