RNN-based counterfactual prediction

This paper proposes an alternative to the synthetic control method (SCM) for estimating the effect of a policy intervention on an outcome over time. Recurrent neural networks (RNNs) are used to predict the counterfactual outcomes of treated units using only the outcomes of control units as predictors. This approach is less susceptible to $p$-hacking because it does not require the researcher to choose predictors or pre-intervention covariates to construct the synthetic control. RNNs do not assume a functional form, can learn nonconvex combinations of control units, and are specifically structured to exploit temporal dependencies in sequential data. I apply the approach to the problem of estimating the long-run impacts of U.S. homestead policy on public school spending.