Single-Period Optimal Inventory Control With Substitution: An End-to-End Framework

Abstract

The paper presents a framework for addressing the single-period inventory control problem with substitutable resources. It introduces an end-to-end approach to determine inventory levels of multiple resource grades to meet stochastic demand at reduced costs. This framework is applicable to various scenarios such as multi-grade resource order decisions, used product procurement, and cloud computing resource allocation. In contrast to traditional Predict-then-Optimize approaches, which suffer from decoupling between demand forecasting and inventory decision-making, the paper leverages neural networks to directly yield inventory control decisions. A re-engineered loss function is proposed to tackle unsupervised learning challenges, demonstrating improved solution quality and faster inference speed compared to conventional Predict-then-Optimize methods through numerical experiments on three datasets with different data distributions. The research enhances decision efficiency and quality in high-frequency decision-making scenarios. Future directions for model improvement are also discussed. Note to Practitioners—This research offers an end-to-end inventory control model using neural networks to manage stock levels for goods with uncertain demand. The model determines inventory decisions directly from observable data, skipping traditional forecasting steps. It is designed for real-time use and can improve efficiency in sectors like remanufacturing and cloud services. Consider integrating this model into your operations for faster, data-driven inventory management. It could help reduce costs and enhance responsiveness to fluctuating demands. Future work will explore extending this approach to more complex scenarios.