Abstract
The increasing threat of credit card fraud in the digital age necessitates robust and intelligent detection systems. This study investigates the application of machine learning algorithms—Logistic Regression, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN)—to identify fraudulent credit card transactions. Using a real-world dataset, the research addresses issues of class imbalance with the SMOTE technique and develops models capable of classifying transactions with high precision and recall. A web-based fraud detection system is also designed to visualize and evaluate model performance. The results highlight the effectiveness of machine learning in real-time fraud detection and present a scalable system framework suitable for deployment in modern financial infrastructures.

This publication has 9 references indexed in Scilit: