Using Machine Learning to Target Treatment: The Case of Household Energy Use
研究使用因果森林算法，通过选择性目标定位提升一项随机行为干预项目的效果，发现预处理用电量和房屋价值是预测异质性处理效应的最强因素，且因果森林能显著提高社会净收益。
Abstract We test the ability of causal forests to improve, through selective targeting, the effectiveness of a randomised program providing repeated behavioural nudges towards household energy conservation. The average treatment effect of the program is a monthly electricity reduction of 9 kilowatt hours (kWh), but the full distribution of predicted reductions ranges from roughly 1 to 33 kWh. Pre-treatment electricity consumption and home value are the strongest predictors of differential treatment effects. In a pair of targeting exercises, use of the causal forest increases social net benefits of the nudge program by a factor of 3–5 relative to the status quo. Using models calibrated with earlier program waves to choose households to target in later ones, we estimate that the forest produces more benefits than five other alternative predictive models. Bootstrapping to generate confidence intervals, we find the forest’s advantage to be statistically significant relative to some, but not all, of these alternatives.