CURLS: Causal Rule Learning for Subgroups with Significant Treatment Effect

TL;DR

CURLS is a novel rule learning method that identifies interpretable subgroups with significant treatment effects, improving the accuracy and interpretability of heterogeneous treatment effect estimation.

Contribution

It introduces a discrete optimization framework and an iterative algorithm for causal rule learning, enhancing subgroup description and effect estimation accuracy.

Findings

CURLS finds subgroups with 16.1% higher estimated effects

Variance in effect estimates is reduced by 12.0%

Maintains or improves interpretability and accuracy compared to state-of-the-art methods

Abstract

In causal inference, estimating heterogeneous treatment effects (HTE) is critical for identifying how different subgroups respond to interventions, with broad applications in fields such as precision medicine and personalized advertising. Although HTE estimation methods aim to improve accuracy, how to provide explicit subgroup descriptions remains unclear, hindering data interpretation and strategic intervention management. In this paper, we propose CURLS, a novel rule learning method leveraging HTE, which can effectively describe subgroups with significant treatment effects. Specifically, we frame causal rule learning as a discrete optimization problem, finely balancing treatment effect with variance and considering the rule interpretability. We design an iterative procedure based on the minorize-maximization algorithm and solve a submodular lower bound as an approximation for the original. Quantitative experiments and qualitative case studies verify that compared with state-of-the-art methods, CURLS can find subgroups where the estimated and true effects are 16.1% and 13.8% higher and the variance is 12.0% smaller, while maintaining similar or better estimation accuracy and rule interpretability. Code is available at https://osf.io/zwp2k/.