Machine Learning for Variance Reduction in Online Experiments
Abstract
We consider the problem of variance reduction in randomized controlled trials, through the use of covariates correlated with the outcome but independent of the treatment. We propose a machine learning regression-adjusted treatment effect estimator, which we call MLRATE. MLRATE uses machine learning predictors of the outcome to reduce estimator variance. It employs cross-fitting to avoid overfitting biases, and we prove consistency and asymptotic normality under general conditions. MLRATE is robust to poor predictions from the machine learning step: if the predictions are uncorrelated with the outcomes, the estimator performs asymptotically no worse than the standard difference-in-means estimator, while if predictions are highly correlated with outcomes, the efficiency gains are large. In A/A tests, for a set of 48 outcome metrics commonly monitored in Facebook experiments the estimator has over 70% lower variance than the simple difference-in-means estimator, and about 19% lower variance than the common univariate procedure which adjusts only for pre-experiment values of the outcome.
Cite
@article{arxiv.2106.07263,
title = {Machine Learning for Variance Reduction in Online Experiments},
author = {Yongyi Guo and Dominic Coey and Mikael Konutgan and Wenting Li and Chris Schoener and Matt Goldman},
journal= {arXiv preprint arXiv:2106.07263},
year = {2022}
}