Insurance Fraud Detection: A Statistically-Validated Network Approach

Tumminello, Michele; Consiglio, Andrea; Vassallo, Pietro; Cesari, Riccardo; Farabullini, Fabio

doi:10.2139/ssrn.4189489

Cited by 2 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Duval et al (2023) further use unsupervised learning, including isolation forests, to derive anomaly profiles of driving behavior and identified a predictive relationship to the probability of automobile insurance claims. Tumminello et al (2023) develop filter rules to identify the criminal infrastructures of fraudsters in extensive networks.…”

Section: Literature Reviewmentioning

confidence: 99%

Detecting insurance fraud using supervised and unsupervised machine learning

Debener

Heinke

Kriebel

2023

J of Risk & Insurance

View full text Add to dashboard Cite

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.

show abstract

Section: Literature Reviewmentioning

confidence: 99%