Integrating Demand Forecasting with Inventory Management Models for Decision Support Systems

Abstract

Demand forecasting and inventory management are critical components of efficient supply chain operations, yet their integration into decision support systems (DSS) remains a challenge for many organizations. This study explores a comprehensive approach to integrating demand forecasting models with inventory management strategies to enhance decision-making and operational efficiency. By leveraging advanced forecasting techniques, including machine learning algorithms, and integrating them with dynamic inventory control models, this research proposes a robust framework for real-time, data-driven decision-making. The methodology incorporates historical sales data, market trends, and seasonal variations to develop predictive models that feed directly into inventory management systems. Results demonstrate significant improvements in forecasting accuracy, inventory cost optimization, and reduced stockouts. The integrated approach, validated through simulations and performance metrics such as root mean square error (RMSE) and inventory key performance indicators (KPIs), highlights the transformative potential of these technologies in supply chain management. This research underscores the value of decision support systems in bridging the gap between demand forecasting and inventory control, offering practical solutions for businesses aiming to enhance their supply chain resilience and efficiency.