Published October 31, 2019
| Published + Supplemental Material
Journal Article
Open
Election forensics: Using machine learning and synthetic data for possible election anomaly detection
- Creators
- Zhang, Mali
-
Alvarez, R. Michael
- Levin, Ines
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.
Additional Information
© 2019 Zhang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Received: February 13, 2019; Accepted: September 30, 2019; Published: October 31, 2019. The authors thank Lucas Núñez and Julia Pomares for their work on related projects. Data Availability: The replication materials have been deposited in Dataverse (https://doi.org/10.7910/DVN/YZRJWD), and the documentation for the replication materials contains relevant information for accessing the original data. The electoral data used in the paper were obtained from Datos Argentina, the official Argentina government open data site. Official demographic statistics were downloaded from the website of the National Institute of Statistics and Census of Argentina (INDEC). 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. The authors have declared that no competing interests exist.Attached Files
Published - journal.pone.0223950.pdf
Supplemental Material - pone.0223950.s001.pdf
Files
journal.pone.0223950.pdf
Files
(2.1 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:32df6ce98d391f5c09139af63051547a
|
1.9 MB | Preview Download |
|
md5:4a60ed96ddc674060bf3becacd866eff
|
184.4 kB | Preview Download |
Additional details
- PMCID
- PMC6822750
- Eprint ID
- 99672
- Resolver ID
- CaltechAUTHORS:20191105-103337302
- John and Dora Haynes Foundation
- Created
-
2019-11-05Created from EPrint's datestamp field
- Updated
-
2023-06-01Created from EPrint's last_modified field