Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice
For practitioners in economics and transportation who need choice models that are both accurate and economically valid, this work provides a practical fix for a known failure mode of foundation models.
Tabular foundation models for discrete choice often violate economic logic (e.g., price increases raise demand). The authors propose a two-stage adapter that enforces economic constraints while preserving accuracy, recovering up to 13 percentage points over standard logit models with perfect consistency.
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.