Anomaly Detection and Automated Labeling for Voter Registration File Changes

TL;DR

This paper presents machine learning methods for detecting and explaining changes in voter registration files to help election officials monitor and secure voter databases effectively.

Contribution

It introduces unsupervised anomaly detection techniques and a new model that uses metadata to identify the causes of database modifications in voter registration files.

Findings

Statistical models and non-negative matrix factorization effectively detect anomalies.

Deployed methods during 2019-2020 in collaboration with Iowa Secretary of State.

A new model predicts causes of modifications using historical and demographic data.

Abstract

Voter eligibility in United States elections is determined by a patchwork of state databases containing information about which citizens are eligible to vote. Administrators at the state and local level are faced with the exceedingly difficult task of ensuring that each of their jurisdictions is properly managed, while also monitoring for improper modifications to the database. Monitoring changes to Voter Registration Files (VRFs) is crucial, given that a malicious actor wishing to disrupt the democratic process in the US would be well-advised to manipulate the contents of these files in order to achieve their goals. In 2020, we saw election officials perform admirably when faced with administering one of the most contentious elections in US history, but much work remains to secure and monitor the election systems Americans rely on. Using data created by comparing snapshots taken of VRFs over time, we present a set of methods that make use of machine learning to ease the burden on analysts and administrators in protecting voter rolls. We first evaluate the effectiveness of multiple unsupervised anomaly detection methods in detecting VRF modifications by modeling anomalous changes as sparse additive noise. In this setting we determine that statistical models comparing administrative districts within a short time span and non-negative matrix factorization are most effective for surfacing anomalous events for review. These methods were deployed during 2019-2020 in our organization's monitoring system and were used in collaboration with the office of the Iowa Secretary of State. Additionally, we propose a newly deployed model which uses historical and demographic metadata to label the likely root cause of database modifications. We hope to use this model to predict which modifications have known causes and therefore better identify potentially anomalous modifications.