English

Model Selection in Utility-Maximizing Binary Prediction

Econometrics 2021-09-29 v3

Abstract

The maximum utility estimation proposed by Elliott and Lieli (2013) can be viewed as cost-sensitive binary classification; thus, its in-sample overfitting issue is similar to that of perceptron learning. A utility-maximizing prediction rule (UMPR) is constructed to alleviate the in-sample overfitting of the maximum utility estimation. We establish non-asymptotic upper bounds on the difference between the maximal expected utility and the generalized expected utility of the UMPR. Simulation results show that the UMPR with an appropriate data-dependent penalty achieves larger generalized expected utility than common estimators in the binary classification if the conditional probability of the binary outcome is misspecified.

Keywords

Cite

@article{arxiv.1903.00716,
  title  = {Model Selection in Utility-Maximizing Binary Prediction},
  author = {Jiun-Hua Su},
  journal= {arXiv preprint arXiv:1903.00716},
  year   = {2021}
}

Comments

Accepted by the Journal of Econometrics

R2 v1 2026-06-23T07:56:18.443Z