Discrete-Choice Model with Generalized Additive Utility Network

TL;DR

This paper introduces GAUNet, a neural network architecture for discrete-choice models that balances high prediction accuracy with improved interpretability, using generalized additive utility functions.

Contribution

The paper presents GAUNet, a novel neural network architecture based on generalized additive models, enhancing interpretability in discrete-choice modeling.

Findings

GAUNet achieves prediction accuracy comparable to ASU-DNN.

GAUNet offers improved interpretability over existing neural network models.

Models tested on Tokyo trip survey data demonstrate effectiveness.

Abstract

Discrete-choice models are a powerful framework for analyzing decision-making behavior to provide valuable insights for policymakers and businesses. Multinomial logit models (MNLs) with linear utility functions have been used in practice because they are ease to use and interpretable. Recently, MNLs with neural networks (e.g., ASU-DNN) have been developed, and they have achieved higher prediction accuracy in behavior choice than classical MNLs. However, these models lack interpretability owing to complex structures. We developed utility functions with a novel neural-network architecture based on generalized additive models, named generalized additive utility network ( GAUNet), for discrete-choice models. We evaluated the performance of the MNL with GAUNet using the trip survey data collected in Tokyo. Our models were comparable to ASU-DNN in accuracy and exhibited improved interpretability compared to previous models.