Predicting the Fraud in Auto Insurance Claims

Project Code :TCMAPY1110

Objective

This project aims to evaluate the effectiveness of Decision Tree, Logistic Regression, XGBoost, and Multi-Layer Perceptron (MLP) algorithms in predicting fraudulent auto insurance claims. By conducting a comparative analysis of these methods using various metrics, including accuracy, precision, recall, and F1-score, the study seeks to provide insights into their capabilities and limitations for enhancing fraud detection in the auto insurance industry.

Abstract

Fraudulent claims pose significant challenges to the auto insurance industry, leading to substantial financial losses and operational inefficiencies. In this study, we explore the effectiveness of four machine learning algorithms Decision Tree, Logistic Regression, XGBoost, and Multi-Layer Perceptron (MLP) in predicting fraudulent auto insurance claims. Utilizing a comprehensive dataset comprising various features relevant to claim authenticity, we conduct a comparative analysis of these algorithms. Our investigation involves feature engineering, model training, and performance evaluation using metrics such as accuracy, precision, recall, and F1-score. The results offer insights into the strengths and limitations of each approach in identifying fraudulent activities within auto insurance claims. Ultimately, this research contributes to the development of robust fraud detection systems, aiding insurance companies in mitigating financial risks and enhancing operational efficiency.

Keywords: Decision Tree, Logistic Regression, XGBoost, and Multi-Layer Perceptron (MLP)

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.