In this paper, we explored the application of both the Random Forest and K-Nearest Neighbors (KNN) algorithms for fraud detection. Fraudulent activities pose significant threats to various industries, making their detection crucial. We reviewed related works on fraud detection, highlighting the effectiveness of both the Random Forest and KNN methods. We proposed a system utilizing a combination of Random Forest and KNN models for credit card fraud detection, detailing its architecture and methodology. The system preprocesses and splits data, trains the models, and evaluates their performance on a testing set. We analyzed the results, demonstrating the accuracy, robustness, and scalability of the proposed system. Additionally, we presented data on the most common hours for fraudulent transactions and the top jobs associated with them. Overall, this study emphasizes the efficacy of utilizing both Random Forest and KNN algorithms in mitigating the risks associated with fraud and offers a valuable tool for safeguarding against financial malfeasance.