Counterfactual time-series prediction with encoder-decoder networks

This paper proposes an alternative to the synthetic control method (SCM) for estimating the effect of a policy intervention on an outcome over time. Encoder-decoder recurrent neural networks (RNNs) are used to predict counterfactual time-series of treated unit outcomes using only the outcomes of control units as inputs. Unlike SCM, the proposed method does not rely on pre-intervention covariates, allows for nonconvex combinations of control units, and can handle multiple treated units. In empirical and simulated data applications, RNN-based models outperform SCM in terms of predictive accuracy while using much less information to produce counterfactual predictions.