# Modeling Choice via Self-Attention

arXiv: https://arxiv.org/abs/2311.07607 · HTML: https://mlsanity.com/paper/2311.07607/

## Key facts

- Cited by 1 papers in the map (data through 7 Oct 2026).
- Builds on 4 of its 28 references that are in the map.
- First posted on arXiv 11 Nov 2023.

## Builds on (most cited first, 4 of 4)

- [Decision Forest: A Nonparametric Approach to Modeling Irrational Choice](https://mlsanity.com/paper/1904.11532/) (2019)
- [Representing Random Utility Choice Models with Neural Networks](https://mlsanity.com/paper/2207.12877/) (2022)
- [On the estimation of discrete choice models to capture irrational customer behaviors](https://mlsanity.com/paper/2109.03882/) (2021)
- [Deep Learning for Choice Modeling](https://mlsanity.com/paper/2208.09325/) (2022)

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

- [DeepHalo: A Neural Choice Model with Controllable Context Effects](https://mlsanity.com/paper/2601.04616/) (2026)

## Abstract (arXiv)

Models of choice are a fundamental input to many now-canonical optimization problems in the field of Operations Management, including assortment, inventory, and price optimization. Naturally, accurate estimation of these models from data is a critical step in the application of these optimization problems in practice. Concurrently, recent advancements in deep learning have sparked interest in integrating these techniques into choice modeling. However, there is a noticeable research gap at the intersection of deep learning and choice modeling, particularly with both theoretical and empirical foundations. Thus motivated, we first propose a choice model that is the first to successfully (both theoretically and practically) leverage a modern neural network architectural concept (self-attention). Theoretically, we show that our attention-based choice model is a low-rank generalization of the Halo Multinomial Logit (Halo-MNL) model. We prove that whereas the Halo-MNL requires Omega(m2) data samples to estimate, where m is the number of products, our model supports a natural nonconvex estimator (in particular, that which a standard neural network implementation would apply) which admits a near-optimal stationary point with O(m) samples. Additionally, we establish the first realistic-scale benchmark for choice model estimation on real data, conducting the most extensive evaluation of existing models to date, thereby highlighting our model's superior performance.