CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING

Abstract

Credit card transactions have become one of the most popular methods of digital payment due to the rapid growth of online banking, e-commerce, and cashless transactions. However, the increasing use of digital payment systems has also resulted in a significant rise in fraudulent activities. Credit card fraud causes major financial losses for banks, merchants, and customers worldwide. Traditional fraud detection methods are often unable to identify complex and evolving fraudulent transaction patterns in real time. Therefore, there is a growing need for intelligent and automated fraud detection systems that can accurately identify suspicious activities while minimizing false alarms. This project proposes a Machine Learning-based Credit Card Fraud Detection System capable of analyzing transaction data and identifying fraudulent transactions efficiently. The system uses historical transaction datasets containing information such as transaction amount, time, customer behavior, and transaction patterns. Data preprocessing techniques such as normalization, missing value handling, and imbalance correction are applied to improve data quality and model performance. Various Machine Learning algorithms including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), and Artificial Neural Networks (ANN) are used to classify transactions as genuine or fraudulent.