Detecting insurance fraud using supervised and unsupervised machine learning

Jörn Debener, Volker Heinke and Johannes Kriebel

Journal of Risk & Insurance, 2023, vol. 90, issue 3, 743-768

Abstract: Fraud is a significant issue for insurance companies, generating much interest in machine learning solutions. Although supervised learning for insurance fraud detection has long been a research focus, unsupervised learning has rarely been studied in this context, and there remains insufficient evidence to guide the choice between these branches of machine learning for insurance fraud detection. Accordingly, this study evaluates supervised and unsupervised learning using proprietary insurance claim data. Furthermore, we conduct a field experiment in cooperation with an insurance company to investigate the performance of each approach in terms of identifying new fraudulent claims. We derive several important findings. Unsupervised learning, especially isolation forests, can successfully detect insurance fraud. Supervised learning also performs strongly, despite few labeled fraud cases. Interestingly, unsupervised and supervised learning detect new fraudulent claims based on different input information. Therefore, for implementation, we suggest understanding supervised and unsupervised methods as complements rather than substitutes.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://doi.org/10.1111/jori.12427

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bla:jrinsu:v:90:y:2023:i:3:p:743-768

Ordering information: This journal article can be ordered from
http://www.wiley.com/bw/subs.asp?ref=0022-4367

Access Statistics for this article

Journal of Risk & Insurance is currently edited by Joan T. Schmit

More articles in Journal of Risk & Insurance from The American Risk and Insurance Association Contact information at EDIRC.
Bibliographic data for series maintained by Wiley Content Delivery ().