RNN-based counterfactual time-series prediction

Explore this paper's citation graph

Summary

Recurrent neural networks are used to predict counterfactual time-series of treated unit outcomes using only the outcomes of control units as inputs, and RNNs outperform SCM in terms of recovering experimental estimates from a field experiment extended to a time- series observational setting.

Type
article
Published
2018-05-01
Cited by
5
References
28
Access
Open access

Keywords

Counterfactual thinking, Recurrent neural network, Exploit, Computer science, Representation (politics)

References

Cited by

Related papers