Abstract
Tabular foundation models (TFMs) generate predictions on structured data via in-context learning, without task-specific estimation. We investigate whether TFMs can be effectively applied to discrete choice, a central demand estimation framework in marketing and operations, and find that directly applying TFMs yields limited performance.
Problem Analysis
The gap is structural: TFMs assume row-independent observations, whereas discrete choice is inherently set-valued and subject to persistent consumer preference heterogeneity. We propose a reformulation that encodes both choice-set dependence and individual heterogeneity within a row-based learning framework.
Experimental Results
Evaluated on a yogurt scanner panel, individual-level heterogeneity encoding is the dominant driver of predictive accuracy. The best reformulation outperforms hierarchical Bayesian estimation by 8% in holdout log-likelihood and 3.6% in hit rate, running 16 times faster, a practical advantage for large-scale demand estimation. The advantage is largest in the medium-data regime (10--40 purchase occasions per consumer), where parametric Bayesian shrinkage most distorts estimates for atypical consumers.
Fine-tuning on population choice data provides additional gains for consumers with shallow purchase histories, where in-context learning has limited individual-specific signal to condition on.
These results establish a principled approach for applying foundation models to consumer choice problems more broadly.
Blogger's Review: The application of TFMs in discrete choice estimation is noteworthy, particularly the method of encoding individual heterogeneity, which significantly enhances predictive accuracy and efficiency, showcasing the potential of foundation models in real-world business scenarios.