Neural Network Approach to Demand Estimation and Dynamic Pricing in Retail

TL;DR

This paper introduces a neural network-based demand estimation method that outperforms traditional econometric models, especially under limited price variation, by better capturing consumer preferences and demand-price relationships.

Contribution

The paper presents a novel deep learning approach for demand estimation that improves accuracy and robustness over econometric methods in retail settings.

Findings

Neural network model reduces mean squared error of demand estimates by nearly threefold.

ML model consistently predicts negative demand-price relationship in all cases.

Model effectively incorporates product characteristics and competitor prices.

Abstract

This paper contributes to the literature on parametric demand estimation by using deep learning to model consumer preferences. Traditional econometric methods often struggle with limited within-product price variation, a challenge addressed by the proposed neural network approach. The proposed method estimates the functional form of the demand and demonstrates higher performance in both simulations and empirical applications. Notably, under low price variation, the machine learning model outperforms econometric approaches, reducing the mean squared error of initial price parameter estimates by nearly threefold. In empirical setting, the ML model consistently predicts a negative relationship between demand and price in 100% of cases, whereas the econometric approach fails to do so in 20% of cases. The suggested model incorporates a wide range of product characteristics, as well as prices of other products and competitors.