The Right Tool for the Job? Assessing the Use of Artificial Intelligence for Identifying Administrative Errors

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This article explores the extent to which machine learning can be used to detect administrative errors. It concentrates on administrative errors in unemployment insurance (UI) decisions, which give rise to a public values conflict between efficiency and effectiveness. This conflict is first described and then highlighted in the history of the US UI regime. Machine learning may not only mitigate this conflict but it may also help to combat fraud and reduce the backlog of claims associated with economic crises such as the COVID-19 pandemic. The article uses data about improper UI payments throughout the US from 2002 through 2018 to analyze the accuracy of random forests and deep learning models. We find that a random forest model using gradient descent boosting is more accurate, along several measures, than every deep learning model tested. This finding could be explained by the goodness-of-fit between the machine learning method and the available data. Alternatively, deep learning performance could be attenuated by necessary limits to publicly-accessible claims data.

Original languageEnglish (US)
Title of host publicationProceedings of the 22nd Annual International Conference on Digital Government Research
Subtitle of host publicationDigital Innovations for Public Values: Inclusive Collaboration and Community, DGO 2021
EditorsJooho Lee, Gabriela Viale Pereira, Sungsoo Hwang
PublisherAssociation for Computing Machinery
Pages15-26
Number of pages12
ISBN (Electronic)9781450384926
DOIs
StatePublished - Jun 9 2021
Event22nd Annual International Conference on Digital Government Research: Digital Innovations for Public Values: Inclusive Collaboration and Community, DGO 2021 - Virtual, Online, United States
Duration: Jun 9 2021Jun 11 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference22nd Annual International Conference on Digital Government Research: Digital Innovations for Public Values: Inclusive Collaboration and Community, DGO 2021
Country/TerritoryUnited States
CityVirtual, Online
Period6/9/216/11/21

Keywords

  • AI
  • Administrative Errors
  • Public Administration
  • Social Policy
  • Unemployment Insurance

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'The Right Tool for the Job? Assessing the Use of Artificial Intelligence for Identifying Administrative Errors'. Together they form a unique fingerprint.

Cite this