Machine Learning for Strategic Inference
Theoretical Economics
2021-01-26 v1
Abstract
We study interactions between strategic players and markets whose behavior is guided by an algorithm. Algorithms use data from prior interactions and a limited set of decision rules to prescribe actions. While as-if rational play need not emerge if the algorithm is constrained, it is possible to guide behavior across a rich set of possible environments using limited details. Provided a condition known as weak learnability holds, Adaptive Boosting algorithms can be specified to induce behavior that is (approximately) as-if rational. Our analysis provides a statistical perspective on the study of endogenous model misspecification.
Cite
@article{arxiv.2101.09613,
title = {Machine Learning for Strategic Inference},
author = {In-Koo Cho and Jonathan Libgober},
journal= {arXiv preprint arXiv:2101.09613},
year = {2021}
}