Published Paper Details:

Credit card fraud has become a significant threat in the financial sector, with substantial economic implications. The increasing reliance on digital payment systems necessitates the development of advanced techniques for detecting fraudulent activities. Machine learning (ML) has emerged as a powerful tool for identifying and preventing fraudulent transactions by learning from historical data and recognizing suspicious patterns. This paper explores the application of various ML algorithms for credit card fraud detection. We evaluate techniques such as Logistic Regression, Decision Trees, Random Forest, Support Vector Machines, and Neural Networks using a public dataset. Our study emphasizes the importance of data preprocessing, handling imbalanced datasets, and selecting appropriate evaluation metrics. The results demonstrate that ensemble methods, particularly Random Forest, provide high accuracy and robustness in detecting fraud. Future research directions are also suggested, focusing on real-time fraud detection and adaptive learning systems.