• KARTHIKEYAN S
• NIKHILA N
• Ms.B. JIJITHA

This project focuses on implementing Machine Learning algorithms to detect fraudulent credit card transactions. The objective is to analyse a dataset containing transaction records, preprocess it, apply suitable classification algorithms, and evaluate the model's performance to distinguish between legitimate and fraudulent transactions. With the rapid expansion of digital transactions, fraudulent activities have become more sophisticated, requiring advanced solutions beyond traditional rule-based fraud detection systems. Machine learning techniques offer a dynamic and adaptive approach to identifying fraudulent activities by analysing transaction patterns, user behaviour, and statistical anomalies. By leveraging both supervised and unsupervised learning methods, the system can improve fraud detection accuracy while minimizing false positives. The core algorithms used in this project include Logistic Regression, Random Forest, Support Vector Machines (SVM). Additionally, anomaly detection techniques like Isolation Forest and Autoencoders enhance the system's ability to detect unknown fraud patterns. A major challenge in fraud detection is handling imbalanced datasets, as fraudulent transactions are rare. This project employs resampling techniques like SMOTE and cost-sensitive learning to improve detection rates. Performance evaluation metrics such as precision, recall, F1-score, confusion matrix, and ROC-AUC curve assess model efficiency. The expected outcome of this research is to create an intelligent fraud detection system that financial institutions can integrate into their transaction processing systems. The system aims to reduce financial losses due to fraud, enhance security, and improve the overall customer experience by minimizing disruptions caused by false fraud alerts. This project focuses on implementing Machine Learning algorithms to detect fraudulent credit card transactions. The objective is to analyse a dataset containing transaction records, preprocess it, apply suitable classification algorithms, and evaluate the model's performance to distinguish between legitimate and fraudulent transactions. The integration of anomaly detection models further enhances the system’s ability to detect unknown fraud patterns. The outcome of this research aims to assist financial institutions in reducing fraudulent transactions and improving financial security.

CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING

"CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.j257-j261, March-2025, Available :http://www.jetir.org/papers/JETIR2503936.pdf

"CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppj257-j261, March-2025, Available at : http://www.jetir.org/papers/JETIR2503936.pdf