Conducting causal inference with panel data is a core challenge in social science research. We adapt a deep neural architecture for time series forecasting (the N-BEATS algorithm) to more accurately predict the counterfactual evolution of a treated unit had treatment not occurred. Across a range of settings, the resulting estimator ("SyNBEATS") significantly outperforms commonly employed methods (synthetic controls, two-way fixed effects), and attains comparable or more accurate performance compared to recently proposed methods (synthetic difference-in-differences, matrix completion). Our results highlight how advances in the forecasting literature can be harnessed to improve causal inference in panel data settings.

翻译：面板数据的因果推断是社会科学的核⼼挑战之一。我们将深度神经架构（N-BEATS算法）适⽤于时间序列预测，以更准确地预测未发⽣处理时处理单元的⿊暗反事实演变。在多种设定下，由此产⽣的估计器（“SyNBEATS”）显著优于常⽤⽅法（合成对照、双向固定效应），且与近期提出的⽅法（合成双重差分、矩阵补全）相⽐，其性能相当或更优。我们的结果凸显了如何利⽤预测领域的进展来提升面板数据设定下的因果推断。