Fraud detection in motor insurance claims using Machine Learning

Author

Mandunguza, Tendai.

Title

Fraud detection in motor insurance claims using Machine Learning

Abstract

Fraud detection in motor vehicle insurance claims is a critical challenge faced by insurance companies worldwide, impacting their profitability and operational efficiency. This study explores the application of machine learning techniques to enhance fraud detection accuracy in motor vehicle insurance claims. The research leverages a dataset comprising diverse features related to claim characteristics, policy details, and client demographics. Various machine learning algorithms, including Logistic Regression, Random Forest, and XGBoost, are evaluated to identify fraudulent claims effectively. Performance metrics such as precision, recall, and F1-score are used to assess the models' effectiveness. The findings highlight the importance of robust data preprocessing techniques and algorithm selection in improving fraud detection capabilities. Ultimately, this research contributes to enhancing the reliability and efficiency of fraud detection systems in the motor vehicle insurance industry through advanced machine learning methodologies.

Date

June 2024

Publisher

BUSE

Keywords

Fraud detection in motor vehicle insurance claims,

Machine learning techniques,

Logistic Regression,

Random Forest, and XGBoost

Supervisor

Mr. Chaitezvi,