Doubly Robust Counterfactual Classification

TL;DR

This paper introduces a doubly-robust nonparametric estimator for counterfactual classification, enabling decision-making under hypothetical scenarios with robust and efficient inference.

Contribution

It proposes a novel estimator that is robust to model misspecification and compatible with machine learning, advancing counterfactual classification methods.

Findings

Estimator achieves fast $ oot{n}$ convergence rates.

Robustness against nuisance model misspecification.

Effective in recidivism risk prediction simulations.

Abstract

We study counterfactual classification as a new tool for decision-making under hypothetical (contrary to fact) scenarios. We propose a doubly-robust nonparametric estimator for a general counterfactual classifier, where we can incorporate flexible constraints by casting the classification problem as a nonlinear mathematical program involving counterfactuals. We go on to analyze the rates of convergence of the estimator and provide a closed-form expression for its asymptotic distribution. Our analysis shows that the proposed estimator is robust against nuisance model misspecification, and can attain fast $\sqrt{n}$ rates with tractable inference even when using nonparametric machine learning approaches. We study the empirical performance of our methods by simulation and apply them for recidivism risk prediction.