Supervised Learning for the (s,S) Inventory Model with General Interarrival Demands and General Lead Times

TL;DR

This paper introduces a neural network-based supervised learning approach to efficiently approximate steady-state performance measures in complex (s,S) inventory models with general demand and lead time distributions, reducing reliance on costly simulations.

Contribution

It presents a novel neural network framework trained on simulation data to quickly predict inventory system metrics, applicable to non-Markovian systems with general distributions.

Findings

Neural network accurately predicts inventory metrics across diverse parameters.

Small input features like low-order moments suffice for high accuracy.

Framework significantly reduces computational cost compared to traditional simulation.

Abstract

The continuous-review (s,S) inventory model is a cornerstone of stochastic inventory theory, yet its analysis becomes analytically intractable when dealing with non-Markovian systems. In such systems, evaluating long-run performance measures typically relies on costly simulation. This paper proposes a supervised learning framework via a neural network model for approximating stationary performance measures of (s,S) inventory systems with general distributions for the interarrival time between demands and lead times under lost sales. Simulations are first used to generate training labels, after which the neural network is trained. After training, the neural network provides almost instantaneous predictions of various metrics of the system, such as the stationary distribution of inventory levels, the expected cycle time, and the probability of lost sales. We find that using a small number of low-order moments of the distributions as input is sufficient to train the neural networks and to accurately capture the steady-state distribution. Extensive numerical experiments demonstrate high accuracy over a wide range of system parameters. As such, it effectively replaces repeated and costly simulation runs. Our framework is easily extendable to other inventory models, offering an efficient and fast alternative for analyzing complex stochastic systems.