Fraud Detection System for Credit Cards Using Machine Learning

Abstract

Credit card fraud has become a major challenge in the financial sector due to the rapid growth of online and electronic transactions. Traditional rule-based fraud detection methods are often ineffective against evolving fraudulent patterns. This study presents a machine learning–based fraud detection system designed to accurately identify fraudulent credit card transactions in real time. The system employs supervised learning algorithms such as Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting to analyze transaction behavior and classify transactions as legitimate or fraudulent. Data preprocessing techniques including normalization, feature selection, and handling of class imbalance using SMOTE are applied to improve model performance. Experimental results show that ensemble models, particularly Random Forest and Gradient Boosting, achieve high accuracy, precision, and recall, making them suitable for deployment in real-world financial systems. The proposed system enhances transaction security, reduces financial losses, and improves customer trust.