Predicting Propensity to Vote with Machine Learning

TL;DR

This paper demonstrates how machine learning can predict an individual's likelihood to vote based on past actions and attributes, aiding targeted voter outreach and campaigns.

Contribution

It introduces a machine learning framework using TensorFlow to predict voting propensity, building on prior studies with improved methodology and results.

Findings

Matthews correlation coefficient of 0.39 indicating positive predictive performance

Effective use of past voting data for propensity prediction

Validation of machine learning as a tool for political campaign strategies

Abstract

We demonstrate that machine learning enables the capability to infer an individual's propensity to vote from their past actions and attributes. This is useful for microtargeting voter outreach, voter education and get-out-the-vote (GOVT) campaigns. Political scientists developed increasingly sophisticated techniques for estimating election outcomes since the late 1940s. Two prior studies similarly used machine learning to predict individual future voting behavior. We built a machine learning environment using TensorFlow, obtained voting data from 2004 to 2018, and then ran three experiments. We show positive results with a Matthews correlation coefficient of 0.39.