Credit cards have become one of the most widely used electronic payment methods, offering users convenient and flexible financial transactions. The rapid growth of e-commerce, digital banking, and online payment systems has significantly increased the incidence of credit and debit card fraud, posing serious financial and security challenges. Effective fraud detection is essential to safeguard consumers, financial institutions, and the stability of the digital payment ecosystem. Machine learning techniques have emerged as powerful tools for identifying fraudulent transactions by analyzing complex patterns and anomalies in transaction data. This study investigates the application of machine learning algorithms, including Random Forest, Support Vector Machine (SVM), and Multilayer Perceptron (MLP), for detecting credit card fraud. The comparative analysis of these models highlights their effectiveness in improving fraud detection accuracy while minimizing false alarms, thereby supporting secure electronic payment systems and enhancing trust in digital financial services.

 

Keywords: Credit card, Fraud detection, Artificial intelligence, Machine learning, Classification, Imbalance.