Optimization of supply chain strategies through DDMRP simulations and machine learning models

This thesis investigates the optimization of supply chain strategies by integrating Demand-Driven Material Requirements Planning (DDMRP) with machine learning models. Supply chain management, a critical component of modern business operations, faces increasing challenges due to globalization, digital innovation, and unpredictable disruptions. While traditional Material Requirements Planning (MRP) systems remain widely used, their limitations in handling complex and volatile environments have driven the need for more adaptive approaches. DDMRP offers a dynamic alternative, aligning material flows with actual demand to enhance responsiveness and resilience. This research proposes a novel methodology combining DDMRP with machine learning algorithms to analyze and predict optimal inventory management strategies. By simulating a three-node supply chain under varying conditions and employing machine learning techniques to model decision-making, the study aims to identify cost-effective strategies that improve operational efficiency and adaptability. The results demonstrate how this integrated approach can support managers in navigating uncertainty, reducing costs, and increasing supply chain resilience, offering a valuable contribution to the evolving field of supply chain optimization.