Profit-Aligned CATE Estimation: Reconciling Policy Learning and Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Timoshenko, Artem, Waisman, Caio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918452839579648
author Timoshenko, Artem
Waisman, Caio
author_facet Timoshenko, Artem
Waisman, Caio
contents We propose a framework that aligns Conditional Average Treatment Effect (CATE) estimation with profit maximization. Our method recognizes that, for customers with extreme treatment effects, additional estimation accuracy is unlikely to change the recommended actions. In contrast, accuracy is critical near the decision boundary, where treatment effects are close to treatment costs. Our approach optimizes a novel objective function that concentrates learning capacity along this boundary. The proposed objective is Fisher consistent with respect to the original profit function and yields a consistent estimator for CATEs. Theoretically, our framework unifies standard plug-in optimization and direct policy optimization as limiting cases of the same optimization problem. We further show that entropy-regularized policy optimization is a special case of our framework. This result has a direct practical implication: firms can recover consistent CATE estimates from existing profit-maximization pipelines. We use synthetic data to demonstrate how the proposed framework allows firms to explicitly navigate the trade-off between global prediction accuracy and profit maximization.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13400
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Profit-Aligned CATE Estimation: Reconciling Policy Learning and Inference
Timoshenko, Artem
Waisman, Caio
Econometrics
Machine Learning
We propose a framework that aligns Conditional Average Treatment Effect (CATE) estimation with profit maximization. Our method recognizes that, for customers with extreme treatment effects, additional estimation accuracy is unlikely to change the recommended actions. In contrast, accuracy is critical near the decision boundary, where treatment effects are close to treatment costs. Our approach optimizes a novel objective function that concentrates learning capacity along this boundary. The proposed objective is Fisher consistent with respect to the original profit function and yields a consistent estimator for CATEs. Theoretically, our framework unifies standard plug-in optimization and direct policy optimization as limiting cases of the same optimization problem. We further show that entropy-regularized policy optimization is a special case of our framework. This result has a direct practical implication: firms can recover consistent CATE estimates from existing profit-maximization pipelines. We use synthetic data to demonstrate how the proposed framework allows firms to explicitly navigate the trade-off between global prediction accuracy and profit maximization.
title Profit-Aligned CATE Estimation: Reconciling Policy Learning and Inference
topic Econometrics
Machine Learning
url https://arxiv.org/abs/2512.13400