ConjointNet: Enhancing Conjoint Analysis for Preference Prediction with Representation Learning
Abstract
Understanding consumer preferences is essential to product design and predicting market response to these new products. Choice-based conjoint analysis is widely used to model user preferences using their choices in surveys. However, traditional conjoint estimation techniques assume simple linear models. This assumption may lead to limited predictability and inaccurate estimation of product attribute contributions, especially on data that has underlying non-linear relationships. In this work, we employ representation learning to efficiently alleviate this issue. We propose ConjointNet, which is composed of two novel neural architectures, to predict user preferences. We demonstrate that the proposed ConjointNet models outperform traditional conjoint estimate techniques on two preference datasets by over 5%, and offer insights into non-linear feature interactions.
Cite
@article{arxiv.2503.11710,
title = {ConjointNet: Enhancing Conjoint Analysis for Preference Prediction with Representation Learning},
author = {Yanxia Zhang and Francine Chen and Shabnam Hakimi and Totte Harinen and Alex Filipowicz and Yan-Ying Chen and Rumen Iliev and Nikos Arechiga and Kalani Murakami and Kent Lyons and Charlene Wu and Matt Klenk},
journal= {arXiv preprint arXiv:2503.11710},
year = {2025}
}