Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yingshuo, Sun, Xian, Li, Yanhang, Fan, Zhichao, Zhuang, Zexin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910258056658944
author Wang, Yingshuo
Sun, Xian
Li, Yanhang
Fan, Zhichao
Zhuang, Zexin
author_facet Wang, Yingshuo
Sun, Xian
Li, Yanhang
Fan, Zhichao
Zhuang, Zexin
contents Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price sometimes increases predicted demand, and implied willingness-to-pay estimates are frequently negative or implausible. We propose a two-stage adapter that embeds foundation model predictions within a utility-maximization framework. In the first stage, we estimate a standard choice model whose parameters are constrained to obey economic theory. In the second stage, we freeze those parameters and train a correction term that incorporates the foundation model's predictions as additional information. The result is a model that inherits the foundation model's accuracy gains while guaranteeing monotonic price-demand relationships under policy perturbation and producing analytically computable trade-off measures. On two transportation datasets, the adapter recovers up to 13 percentage points of accuracy over a standard logit model while maintaining perfect economic consistency, something neither the raw foundation models nor conventional distillation achieve.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26559
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice
Wang, Yingshuo
Sun, Xian
Li, Yanhang
Fan, Zhichao
Zhuang, Zexin
Machine Learning
Artificial Intelligence
Econometrics
Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price sometimes increases predicted demand, and implied willingness-to-pay estimates are frequently negative or implausible. We propose a two-stage adapter that embeds foundation model predictions within a utility-maximization framework. In the first stage, we estimate a standard choice model whose parameters are constrained to obey economic theory. In the second stage, we freeze those parameters and train a correction term that incorporates the foundation model's predictions as additional information. The result is a model that inherits the foundation model's accuracy gains while guaranteeing monotonic price-demand relationships under policy perturbation and producing analytically computable trade-off measures. On two transportation datasets, the adapter recovers up to 13 percentage points of accuracy over a standard logit model while maintaining perfect economic consistency, something neither the raw foundation models nor conventional distillation achieve.
title Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice
topic Machine Learning
Artificial Intelligence
Econometrics
url https://arxiv.org/abs/2605.26559