Abstract

Forecasting demand effectively and managing inventories efficiently are critical components of modern supply chain management. By understanding full scope of demand possibilities, businesses gain ability to fine-tune inventory levels, navigate situations involving stockouts and overstock, and move toward a more resilient and precise supply chain. This thesis focuses on strategies to enhance these critical functions.
We start with examining impact of customer segmentation on forecasting precision by introducing a novel cluster-based demand forecasting framework that harnesses ensemble learning techniques. Our results showcase the effectiveness of the clustered-ensembled approach with minimal forecast errors. However, the constraints related to data availability and segmentation indicate areas that warrant further investigation in future research.
The significance of demand accuracy becomes most apparent when we consider its impact on safety stock. In second objective, we explore multivariate time series forecasting for optimal safety stock and inventory management, utilizing deep learning models and a cost optimization framework. This strategy outperforms individual models, demonstrating enhanced forecasting accuracy and stability across diverse product domains. Calculating safety stock based on proposed demand prediction framework leads to optimized safety stock levels. This not only prevents costly stockouts but also minimizes surplus inventory, resulting in reduced overall holding costs and improved inventory efficiency.
Although the first two objectives provided optimized results, relying on point predictions to calculate safety stock is not ideal. Unlike traditional point forecasting, distribution forecasting aims to cover the entire range of potential demand outcomes, essentially creating a comprehensive map of possibilities. The third objective of this thesis introduces recurrent mixture density networks (RMDNs) for refined distribution demand forecasting and safety stock estimation. These innovative models consistently outperform traditional LSTM models, offering more precise stockout and overstock predictions. This approach not only reduces inventory costs but also enhances supply chain efficiency.
In summary, this thesis provides valuable insights and methodologies for businesses aiming to enhance demand forecasting accuracy and optimize inventory management practices in the retail industry. By leveraging customer segmentation, ensemble deep learning, and distribution forecasting techniques, organizations can enhance decision-making processes, reduce operational costs, and thrive in the dynamic landscape of supply chain operations.