The burgeoning growth of e-commerce and financial technology (Fin Tech) has dramatically increased the volume of online card transactions, leading to a concomitant surge in credit card fraud. This poses a significant threat to card-issuing institutions, merchants, and banks. To address the inherent class imbalance in fraud detection datasets, we employed the Synthetic Minority Oversampling Technique (SMOTE) to augment the minority class. We evaluated the performance of various machine learning (ML) algorithms, including Support Vector Machines (SVM), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Decision Trees (DT), and Extra Trees (ET), on datasets enhanced with SMOTE. To safeguard user privacy, we explored dimensionality reduction techniques. To enhance fraud detection capabilities, we experimented with hybrid models combining AdaBoost with majority voting techniques, we should use advanced technologies which will be useful for remote and distant customers for their normal economic safety status in this technical society.