This research paper presents a comprehensive study that compares different machine-learning models used for detecting credit card fraud. The focus of the study is on the application of federated learning to safeguard user privacy. The models examined in the research include RNN, CNN, LSTM, MLP, RBFNN, GRU, and a novel model called FedMLPNN (Federated MultiLayer-Perceptron Neural Network). The analysis results indicate that the FedMLPNN model outperformed the other models in various key metrics, such as accuracy, precision, F1 score, recall, and AUC. The FedMLPNN model achieved an impressive accuracy rate of 97.34%, demonstrating its exceptional classification capabilities. It also exhibited a low loss value, indicating successful convergence during training. The model showed remarkable recall and precision rates of 97.42% and 97.28% respectively, accurately identifying positive instances while minimizing false positives. Additionally, the high AUC score of 99.63% confirmed its robustness and discriminative power. In contrast, the GRU model performed the worst, achieving an accuracy of only 79.04%. The RNN, CNN, LSTM, MLP, and RBFNN models achieved accuracies ranging from 91.31% to 95.1%. These findings underscore the superiority of the FedMLPNN model in terms of accuracy and overall performance.