Applying Deep Learning to the Newsvendor Problem

TL;DR

This paper introduces a deep learning algorithm that jointly forecasts demand and optimizes inventory order quantities for the newsvendor problem, outperforming traditional methods especially in volatile demand scenarios.

Contribution

It presents a novel integrated deep learning approach that combines demand forecasting and inventory optimization without requiring demand distribution knowledge.

Findings

Outperforms existing data-driven methods on real-world data

Effective for high-volatility demand scenarios

Extensible to other inventory policies like (r,Q)

Abstract

The newsvendor problem is one of the most basic and widely applied inventory models. There are numerous extensions of this problem. If the probability distribution of the demand is known, the problem can be solved analytically. However, approximating the probability distribution is not easy and is prone to error; therefore, the resulting solution to the newsvendor problem may be not optimal. To address this issue, we propose an algorithm based on deep learning that optimizes the order quantities for all products based on features of the demand data. Our algorithm integrates the forecasting and inventory-optimization steps, rather than solving them separately, as is typically done, and does not require knowledge of the probability distributions of the demand. Numerical experiments on real-world data suggest that our algorithm outperforms other approaches, including data-driven and machine learning approaches, especially for demands with high volatility. Finally, in order to show how this approach can be used for other inventory optimization problems, we provide an extension for (r,Q) policies.