Deep Learning for Choice Modeling

TL;DR

This paper introduces deep learning models for choice modeling that effectively capture utility and assortment effects, demonstrating improved performance and interpretability over traditional methods in both synthetic and real data scenarios.

Contribution

It develops novel deep learning-based choice models for feature-free and feature-based settings, addressing computational and sample efficiency issues in existing methods.

Findings

Models accurately recover existing choice models

Demonstrated improved sample efficiency

Effectively captures assortment impacts

Abstract

Choice modeling has been a central topic in the study of individual preference or utility across many fields including economics, marketing, operations research, and psychology. While the vast majority of the literature on choice models has been devoted to the analytical properties that lead to managerial and policy-making insights, the existing methods to learn a choice model from empirical data are often either computationally intractable or sample inefficient. In this paper, we develop deep learning-based choice models under two settings of choice modeling: (i) feature-free and (ii) feature-based. Our model captures both the intrinsic utility for each candidate choice and the effect that the assortment has on the choice probability. Synthetic and real data experiments demonstrate the performances of proposed models in terms of the recovery of the existing choice models, sample complexity, assortment effect, architecture design, and model interpretation.