Seo-young Silvia KimCalifornia Institute of Technology
R. Michael AlvarezCalifornia Institute of Technology
Christina M. RamirezUniversity of California Los Angeles
What can machine learning tell us about who voted in 2016? There are numerous competing turnout theories, and many covariates are required to assess which theory best explains turnout. This paper is a proof-of-concept that machine learning can help overcome this curse of dimensionality and reveal important insights in studies of political phenomena. We use Fuzzy Forests, an extension of Random Forests, to screen variables for a parsimonious but accurate prediction. Using the 2016 Cooperative Congressional Election Study, Fuzzy Forests chose only a few covariates as major correlates of turnout and still boasted high predictive performance. Our analysis provides three important conclusions about 2016 turnout: registration and voting procedures were important, political issues were important (especially Obamacare, climate change, and fiscal policy), but few demographic variables other than age were strongly associated with turnout. We conclude that Fuzzy Forests is an important methodology for studying over-determined questions in social sciences.
pdf : 0.37mb
pdf : 0.18mb