Learning Preferences from Conjoint Data: A Structural Deep Learning Approach

TL;DR

This paper introduces a deep learning-based structural approach to analyze conjoint experiment data, capturing complex preference heterogeneity and providing valid inference on preference parameters.

Contribution

It embeds a neural network within a random utility model, enabling flexible, respondent-specific preference estimation with valid statistical inference.

Findings

Rich preference heterogeneity revealed across studies

Gender effect is near-zero but 83% prefer female candidates

Preferences on opposition and taxation vary sharply within groups

Abstract

Conjoint experiments randomize multidimensional profiles, offering a powerful design for recovering structural preference parameters -- including marginal rates of substitution, willingness to pay, and the distribution of preferences across a population. Yet the dominant approach in political science has focused on nonparametric causal estimands that do not leverage this potential. We propose a structural approach that embeds a deep neural network within a random utility logit model, allowing preference parameters to vary as a fully flexible function of respondent characteristics. The neural network addresses the concern that a parametric specification may not capture the true data generating process, while double/debiased machine learning provides valid inference on average preference parameters. We apply our method to three prominent conjoint studies and find rich preference heterogeneity masked by reduced-form averages: a near-zero gender effect coexists with 83% preferring female candidates, opposition to undemocratic behavior is near-universal but varies sharply in intensity, and progressive tax preferences cut across every partisan subgroup.