A Machine Learning Approach to Detect Credit Fraud

A Machine Learning Approach to Detect Credit Fraud

Ponduru Likhitha, Research Student, Dept of CSE KL UNIVERSITY 2000031680@kluniversity.in

Mohammad Rahamathunnisa, Research Student, Dept of CSE KL UNIVERSITY 2000031825@kluniversity.in

Kanuparthi Prasasthi, Research Student, Dept of CSE KL UNIVERSITY 2000031714@kluniversity.in

Kodukula Subrahmanyam, Prof at KL University,     Dept of CSE smkoduku@kluniversity.in

Venigandla Srilekha, Research Student, Dept of CSE KL UNIVERSITY 2000031770@kluniversity.in

Nagamalleswary, Asst.Prof at KL University, Dept of CSE  nagamalleswary@kluniversity.in

Abstract - Credit fraud poses a significant challenge in the financial sector, leading to substantial financial losses annually. Traditional credit scoring methods often fall short in accurately detecting fraudulent transactions. This research project aims to leverage machine learning algorithms to address this issue by developing intelligent credit scoring systems with a specific focus on credit fraud detection. The objectives include gathering and analyzing a diverse dataset, exploring and evaluating various machine learning algorithms, developing and optimizing models, and evaluating their performance. The study also emphasizes the importance of model interpretability, ethical considerations, and fairness in credit scoring. Through a systematic and objective approach, the research intends to bridge existing gaps in the field, advancing the development of accurate, comprehensible, fair, and practical credit fraud detection systems. The outcomes have the potential to transform credit scoring practices, enabling financial institutions to make informed decisions while mitigating the risk of fraud.

Key Words: Credit Fraud Detection, Machine Learning Algorithms, Credit Scoring, Model Interpretability, Financial Fraud Prevention.