Election forensics: Using machine learning and synthetic data for possible election anomaly detection

Mali Zhang; R Michael Alvarez; Ines Levin

doi:10.1371/journal.pone.0223950

Election forensics: Using machine learning and synthetic data for possible election anomaly detection

PLoS One. 2019 Oct 31;14(10):e0223950. doi: 10.1371/journal.pone.0223950. eCollection 2019.

Authors

Mali Zhang¹, R Michael Alvarez¹, Ines Levin²

Affiliations

¹ Division of Humanities and Social Sciences, California Institute of Technology, Pasadena, CA, United States of America.
² Department of Political Science, University of California, Irvine, CA, United States of America.

Abstract

Assuring election integrity is essential for the legitimacy of elected representative democratic government. Until recently, other than in-person election observation, there have been few quantitative methods for determining the integrity of a democratic election. Here we present a machine learning methodology for identifying polling places at risk of election fraud and estimating the extent of potential electoral manipulation, using synthetic training data. We apply this methodology to mesa-level data from Argentina's 2015 national elections.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Democracy*
Forensic Sciences
Machine Learning*
Risk

Grants and funding

Alvarez thanks the John and Dora Haynes Foundation for supporting his research in this area. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.