ABSTRACT The rapid growth of digital payment systems has significantly increased the number of online financial transactions worldwide. While electronic payment methods provide convenience and efficiency, they also create opportunities for fraudulent activities. Credit card fraud is one of the most common financial crimes, causing substantial economic losses to financial institutions and customers. Traditional fraud detection systems based on manual rules and human verification are often inefficient in identifying complex fraud patterns. Machine learning techniques have emerged as powerful tools for detecting fraudulent transactions by analyzing large volumes of transaction data and identifying hidden patterns. This research proposes a machine learning-based approach for credit card fraud detection using classification algorithms such as Logistic Regression, Random Forest, and Gradient Boosting. Transaction features including transaction amount, time, and behavioral patterns are analyzed to distinguish between legitimate and fraudulent transactions. The performance of the models is evaluated using Accuracy, Precision, Recall, F1-Score, and ROC-AUC metrics. Experimental results indicate that ensemble learning models provide high detection accuracy and can significantly improve fraud detection systems in modern financial networks. Key words: Credit Card Fraud Detection, Machine Learning, Financial Data Analytics, Classification Algorithms, Fraud Detection Systems.