Victor H. Aguiar, Nail Kashaev
arXiv 25 Mar 2026 · Econometrics
arXiv:2603.23993 · PDF · DOI · OpenAlex · Extracted main text
Modern pretrained time-series foundation models can forecast without task-specific training, but they do not fully incorporate economic behavior. We show that teaching them basic economic logic improves how they predict demand using an experimental panel. We fine-tune Amazon Chronos-2, a transformer-based probabilistic time-series model, on synthetic data generated from utility-maximizing agents. We exploit Afriat's theorem, which guarantees that demand satisfies the Generalized Axiom of Revealed Preference (GARP) if and only if it can be generated by maximizing some utility function subject to a budget constraint. GARP is a simple condition to check that allows us to generate time series from a large class of utilities efficiently. The fine-tuned model serves as a rationality-constrained forecasting prior: it learns price-quantity relations from GARP-consistent synthetic histories and then uses those relations to predict the choices of real consumers. We find that fine-tuning on GARP-consistent synthetic data substantially improves prediction relative to zero-shot Chronos-2 at all forecast horizons we study. Our results show that economic theory can be used to generate structured synthetic data that improves foundation-model predictions when the theory implies observable patterns in the data.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Andrews, I (2026) Revealed rationality: Label-free regularization from representation theorems | 0.811 | 4 | 2 | 100% |
| 2 | Varian, H. R (1982) The nonparametric approach to demand analysis | 0.737 | 3 | 2 | 100% |
| 3 | Aguiar, V. H. and Serrano, R (2018) Classifying bounded rationality in limited data sets: a slutsky matrix approach self | 0.644 | 2 | 2 | 100% |
| 4 | Ahn, D., Choi, S., Gale, D., and Kariv, S (2014) Estimating ambiguity aversion in a portfolio choice experiment | 0.644 | 2 | 2 | 100% |
| 5 | Nitsch, F. J., Lüpken, L. M., Lüschow, N., and Kalenscher, T (2022) On the reliability of individual economic rationality measurements | 0.405 | 1 | 1 | 100% |
| 6 | Afriat, S. N (1967) The construction of utility functions from expenditure data | 0.405 | 1 | 1 | 100% |
| 7 | Aguiar, V. H. and Serrano, R (2017) Slutsky matrix norms: The size, classification, and comparative statics of bounded rationality self | 0.405 | 1 | 1 | 100% |
| 8 | Aguiar, V. H. and Kashaev, N (2021) Stochastic revealed preferences with measurement error self | 0.405 | 1 | 1 | 100% |
| 9 | Boelaert, J (2014) revealedPrefs: Revealed Preferences and Microeconomic Rationality | 0.405 | 1 | 1 | 100% |
| 10 | Bronars, S. G (1987) The power of nonparametric tests of preference maximization | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 11 scored citations.