Detection of Vehicle Insurance Claim Fraud: A Fraud Detection Use-Case for the Vehicle Insurance Industry

Abstract

Insurance fraud has accompanied insurance since its inception, but the manner in which these practices and their methods of operation have evolved over time, and the volume and frequency of insurance fraud incidents have recently increased. Vehicle insurance fraud involves conspiring to make false or exaggerated claims involving property damage or personal injuries following an accident. Some common examples include staged accidents where fraudsters deliberately "arrange" for accidents to occur; the use of phantom passengers, where people who were not even at the scene of the accident claim to have suffered grievous injury, and making false personal injury claims where personal injuries are grossly exaggerated. The typical analysis of these datasets includes Algorithms is implemented on the Weka tool depends upon real info represented through from Oracle Databases. In this paper, focusing on detecting vehicle fraud by using, machine learning algorithms, and also the final analysis and conclusion based on performance steps, revealed that J48 is more accurate than Random Forest, Random Tree, Bayes Net and Naïve Bayes but Random Tree has the lowest classification accuracy.