Detecting insurance fraud using supervised and unsupervised machine learning

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.

A Method for Anti-Leakage in Car Insurance Based on the Co-Occurrence Relationship Between Auto Parts

“…Different from traditional single feature classification [11], this method clusters data points based on multiple features they possess, which can more fully reflect the actual relationships between components.…”

Potential fraud and its’ prevention in the implementation of national health insurance at Dadi Regional Hospita

“…Meanwhile, weak internal control in an organization can lead to various frauds. This demonstrates how crucial internal control is in protecting companies against fraud and abuse [18], [19].…”

Enhancing fraud detection in auto insurance and credit card transactions: a novel approach integrating CNNs and machine learning algorithms

“…The considerable financial losses resulting from fraudulent practices have prompted researchers and scholars to strive to develop a robust framework to detect and prevent fraud effectively. Insurance claim fraud represents an intricate and multifaceted phenomenon, often characterized by substantial time and cost requirements for its detection ( Debener, Heinke & Kriebel, 2023 ). Therefore, there is a need to employ machine learning and deep learning to address this issue, and leveraging artificial intelligence for enhanced fraud detection can serve as a strong deterrent against fraudulent activities, offering advantages to insurance companies and their loyal policyholders.…”