Comparative Analysis of Machine Learning Models for Credit Card Fraud Detection

• 1Anna University Chennai, Assistant Professor, Dept. of CSE, Loyola Institute of Technology and Science, Nagercoil, India, IN
• 2Anna University Chennai, Assistant Professor, Dept. of CSE(AIML), Loyola Institute of Technology and Science, Thovalai, Nagarcoil, India, IN
• 3Anna University Chennai, Assistant professor, Department of Computer Science and Engineering Loyola Institute of Technology & Science, Thovalai, IN
• 4Anna University Chennai, Assistant Professor, Dept. of CSE(AIML), Loyola Institute of Technology and Science, Nagercoil, India. , IN
• 5Anna University Chennai, Assistant Professor, Dept. of CSE(AIML), Loyola Institute of Technology and Science, Nagercoil, India, IN

The rapid growth of online transactions has intensified the risk of credit card fraud, posing major challenges to consumers and financial institutions. This study explores various machine learning approaches to accurately distinguish fraudulent transactions from legitimate ones. Using a publicly available dataset, multiple algorithms including Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Naïve Bayes, and Artificial Neural Networks (ANN) were implemented and compared. The models were evaluated on accuracy, precision, recall, and misclassification rates to identify the most effective technique. Experimental findings indicate that SVM achieved the highest accuracy among the tested models, demonstrating strong potential for real-world fraud prevention applications. The results emphasize the importance of data preprocessing, model selection, and continuous improvement to combat the evolving tactics of fraudsters.