Estimating causal effects is crucial in domains like healthcare, economics, and education. Despite advances in machine learning (ML) for estimating conditional average treatment effects (CATE), the practical adoption of these methods remains limited, due to the complexities of implementing, tuning, and validating them. To address these challenges, we formalize the search for an optimal ML pipeline for CATE estimation as a counterfactual Combined Algorithm Selection and Hyperparameter (CASH) optimization. We introduce AutoCATE, the first end-to-end, automated solution for CATE estimation. Unlike prior approaches that address only parts of this problem, AutoCATE integrates evaluation, estimation, and ensembling in a unified framework. AutoCATE enables comprehensive comparisons of different protocols, yielding novel insights into CATE estimation and a final configuration that outperforms commonly used strategies. To facilitate broad adoption and further research, we release AutoCATE as an open-source software package.

Understanding the impact of treatments—like new medications, educational programs, or economic policies—is essential in fields like healthcare, economics, and social science. While machine learning can help estimate these causal effects using data, setting up and tuning these models is often too complex for non-experts. AutoCATE solves this by fully automating this process: it selects, configures, and combines the best machine learning methods to estimate causal effects—without requiring users to make technical decisions. This way, our tool makes causal analyses faster, more accurate, and accessible to anyone, regardless of their expertise in machine learning.