Deep Learning for Perishable Inventory Systems with Human Knowledge

TL;DR

This paper develops deep learning policies for managing perishable inventory with unknown demand and lead times, integrating human knowledge to improve decision-making efficiency and robustness.

Contribution

It introduces end-to-end deep learning approaches that incorporate human-structured policies, demonstrating improved performance over black-box models in perishable inventory management.

Findings

E2E-PIL outperforms E2E-BB in experiments.

Embedding human knowledge reduces model complexity.

Structured policies enhance learning efficiency.

Abstract

Managing perishable products with limited lifetimes is a fundamental challenge in inventory management, as poor ordering decisions can quickly lead to stockouts or excessive waste. We study a perishable inventory system with random lead times in which both the demand process and the lead time distribution are unknown. We consider a practical setting where orders are placed using limited historical data together with observed covariates and current system states. To improve learning efficiency under limited data, we adopt a marginal cost accounting scheme that assigns each order a single lifetime cost and yields a unified loss function for end-to-end learning. This enables training a deep learning-based policy that maps observed covariates and system states directly to order quantities. We develop two end-to-end variants: a purely black-box approach that outputs order quantities directly (E2E-BB), and a structure-guided approach that embeds the projected inventory level (PIL) policy, capturing inventory effects through explicit computation rather than additional learning (E2E-PIL). We further show that the objective induced by E2E-PIL is homogeneous of degree one, enabling a boosting technique from operational data analytics (ODA) that yields an enhanced policy (E2E-BPIL). Experiments on synthetic and real data establish a robust performance ordering: E2E-BB is dominated by E2E-PIL, which is further improved by E2E-BPIL. Using an excess-risk decomposition, we show that embedding heuristic policy structure reduces effective model complexity and improves learning efficiency with only a modest loss of flexibility. More broadly, our results suggest that deep learning-based decision tools are more effective and robust when guided by human knowledge, highlighting the value of integrating advanced analytics with inventory theory.