Fuzzy Forests For Feature Selection in High-Dimensional Survey Data: An Application to the 2020 U.S. Presidential Election

TL;DR

This paper introduces Fuzzy Forests, a novel feature selection method tailored for high-dimensional, correlated social science data, demonstrated through analysis of the 2020 U.S. Presidential Election to identify key electoral factors.

Contribution

The paper presents Fuzzy Forests, an efficient variant of Random Forests for feature selection in high-dimensional correlated datasets, with minimal bias and maintained predictive accuracy.

Findings

Partisan polarization was the strongest factor in the 2020 election.

Fuzzy Forests effectively reduces feature space with minimal bias.

Method maintains predictive performance comparable to standard algorithms.

Abstract

An increasingly common methodological issue in the field of social science is high-dimensional and highly correlated datasets that are unamenable to the traditional deductive framework of study. Analysis of candidate choice in the 2020 Presidential Election is one area in which this issue presents itself: in order to test the many theories explaining the outcome of the election, it is necessary to use data such as the 2020 Cooperative Election Study Common Content, with hundreds of highly correlated features. We present the Fuzzy Forests algorithm, a variant of the popular Random Forests ensemble method, as an efficient way to reduce the feature space in such cases with minimal bias, while also maintaining predictive performance on par with common algorithms like Random Forests and logit. Using Fuzzy Forests, we isolate the top correlates of candidate choice and find that partisan polarization was the strongest factor driving the 2020 presidential election.