Equilibrium Information Aggregation under Machine Learning
arXiv:2607.13670
The paper develops a theoretical model where agents use the Chow‑Liu tree algorithm to process information and studies how this affects equilibrium outcomes in an asset market, finding that market prices aggregate less information than in a rational expectations equilibrium.
Abstract
We introduce a framework for studying the equilibrium effects of machine learning. Agents process information using a Chow and Liu (1968) tree, a widely-used machine learning procedure that admits a closed-form solution. We apply the model to an asset market with dispersed information based on Hellwig (1980). The price mechanism fails to aggregate the information extracted by the algorithm, even approximately. While there are partial equilibrium benefits from access to algorithms, the equilibrium price aggregates less information than the rational equilibrium. Equilibrium typically features diverse world-models, demands, and utilities, even with ex ante identical agents.