An economically-consistent discrete choice model with flexible utility specification based on artificial neural networks

TL;DR

This paper introduces ASS-NN, a neural network-based discrete choice model that balances flexibility and economic consistency, enabling better utility approximation and welfare analysis without predefined utility forms.

Contribution

The paper proposes ASS-NN, a novel neural network model for discrete choice that maintains economic consistency and improves utility estimation over traditional models.

Findings

ASS-NN outperforms traditional MNL models in goodness of fit.

ASS-NN accurately derives marginal utilities and willingness to pay.

Model maintains consistency with RUM theory and fungibility of money.

Abstract

Random utility maximisation (RUM) models are one of the cornerstones of discrete choice modelling. However, specifying the utility function of RUM models is not straightforward and has a considerable impact on the resulting interpretable outcomes and welfare measures. In this paper, we propose a new discrete choice model based on artificial neural networks (ANNs) named "Alternative-Specific and Shared weights Neural Network (ASS-NN)", which provides a further balance between flexible utility approximation from the data and consistency with two assumptions: RUM theory and fungibility of money (i.e., "one euro is one euro"). Therefore, the ASS-NN can derive economically-consistent outcomes, such as marginal utilities or willingness to pay, without explicitly specifying the utility functional form. Using a Monte Carlo experiment and empirical data from the Swissmetro dataset, we show that ASS-NN outperforms (in terms of goodness of fit) conventional multinomial logit (MNL) models under different utility specifications. Furthermore, we show how the ASS-NN is used to derive marginal utilities and willingness to pay measures.