# Discrete Choice Analysis with Machine Learning Capabilities

arXiv: https://arxiv.org/abs/2101.10261 · HTML: https://mlsanity.com/paper/2101.10261/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 45 references that are in the map.
- First posted on arXiv 21 Jan 2021.

## Builds on (most cited first, 7 of 7)

- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Bayesian Estimation of Mixed Multinomial Logit Models: Advances and Simulation-Based Evaluations](https://mlsanity.com/paper/1904.03647/) (2019)
- [Variational Bayesian Inference for Mixed Logit Models with Unobserved Inter- and Intra-Individual Heterogeneity](https://mlsanity.com/paper/1905.00419/) (2019)
- [Enhancing Discrete Choice Models with Representation Learning](https://mlsanity.com/paper/1812.09747/) (2018)
- [Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation](https://mlsanity.com/paper/1812.04528/) (2018)
- [Sparse Covariance Estimation in Logit Mixture Models](https://mlsanity.com/paper/2001.05034/) (2020)
- [Learning Structure in Nested Logit Models](https://mlsanity.com/paper/2008.08048/) (2020)

## Built on by (most cited first, 1 of 1)

- [Enhancing Travel Choice Modeling with Large Language Models: A Prompt-Learning Approach](https://mlsanity.com/paper/2406.13558/) (2024)

## Abstract (arXiv)

This paper discusses capabilities that are essential to models applied in policy analysis settings and the limitations of direct applications of off-the-shelf machine learning methodologies to such settings. Traditional econometric methodologies for building discrete choice models for policy analysis involve combining data with modeling assumptions guided by subject-matter considerations. Such considerations are typically most useful in specifying the systematic component of random utility discrete choice models but are typically of limited aid in determining the form of the random component. We identify an area where machine learning paradigms can be leveraged, namely in specifying and systematically selecting the best specification of the random component of the utility equations. We review two recent novel applications where mixed-integer optimization and cross-validation are used to algorithmically select optimal specifications for the random utility components of nested logit and logit mixture models subject to interpretability constraints.