Author: S. Hanish,V. Savithri,S.danvanth,K.abhishek
Date Published: 02 May 2023
Insurance fraud is a significant problem for the insurance industry, and auto insurance fraud is one of the major areas of concern. This paper presents a study on insurance fraud detection using classification techniques. The objective of the study is to create a system capable of detecting fraudulent auto insurance claims by analyzing a vehicle insurance dataset. The study involves preprocessing the data, performing feature selection and engineering, building classification models, and evaluating the models using various metrics. The models used in the study include decision tree, logistic regression, random forest, and support vector machine. The evaluation metrics include confusion matrix, F1 score, precision, and accuracy. The study shows that the support vector machine model achieved the best performance with an accuracy rating of 83% and an F1 score of 89.31%.