Prof. Hare on Swing Voters and Machine Learning

In an article in Political Analysis, Prof. Hare uses complex, machine learning algorithms to gain insight into swing voting.  "[We] use of an ensemble of supervised machine learning methods to predict swing voters in the 2012, 2016, and 2020 U.S. presidential elections. . . .  Specifically, we demonstrate that the learning ensemble produces well-calibrated and externally valid predictions of swing voter propensity."