Agentic Economic Modeling

Bohan Zhang, Jiaxuan Li, Ali Hortacsu, Xiaoyang Ye, Victor Chernozhukov, Anqi Ni, Edward W Huang

Keywords: Econometrics, Causal Inference, Bias Correction

TL;DR: We propose Agentic Economic Modeling (AEM), a framework that uses LLM personas with learned bias correction to align synthetic choices to small-sample human data, enabling reliable demand and treatment-effect estimation at scale.

Abstract: We introduce Agentic Economic Modeling (AEM), a framework that aligns synthetic LLM choices with small-sample human evidence for reliable econometric inference. AEM first generates task-conditioned synthetic choices via LLMs, then learns a bias-correction mapping from task features and raw LLM choices to human-aligned choices, upon which standard econometric estimators perform inference to recover demand elasticities and treatment effects. We validate AEM in two experiments. In a large scale conjoint study with millions of observations, using only 10\% of the original data to fit the correction model lowers the error of the demand-parameter estimates, while uncorrected LLM choices even increase the errors. In a regional field experiment, a mixture model calibrated on 10\% of geographic regions estimates an out-of-domain treatment effect of -65$\pm$10 bps, closely matching the full human experiment (-60$\pm$8 bps). Under time-wise extrapolation, training with only day-one human data yields -24 bps (95\% CI: [-26, -22], p$<$1e-5), improving over the human-only day-one baseline (-17 bps, 95\% CI: [-43, +9], p=0.2049). These results demonstrate AEM's potential to improve RCT efficiency and establish a foundation method for LLM-based counterfactual generation.

Submission Type: Emerging

Submission Number: 258