Credit Card Fraud Detection: Machine Learning and Data Analytical Approach for Accuracy and Comparative Analysis

Credit card fraud detection is a vital challenge for investment firms, requiring advanced techniques to identify fraudulent transactions efficiently. This study evaluates several machine learning algorithms—Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), k-Nearest Neighbors (KNN), Recurrent Neural Network (RNN), and Support Vector Machine (SVM)—for their performance in fraud detection. Using publicly available credit card transaction datasets, the models are compared based on metrics like accuracy, precision, recall, F1-score, and AUC-ROC. Results show that ensemble methods like Random Forest and SVM offer the best accuracy and robustness, while deep learning models such as RNN also show strong potential for detecting complex fraud patterns. The findings provide significant perspectives into selecting the most efficient machine learning techniques for real-time fraud detection in financial systems. The conclusions of this study aid in the advancement of more efficient, scalable, and precise fraud detection models in finance.