Credit card fraud detection  and risk management strategies:  A deep learning-based approach for EU banks
Credit card fraud detection  and risk management strategies:  A deep learning-based approach for EU banks

Summary/Abstract: This study explores supervised ML-DL based approaches for en-hancing credit card fraud detection and improving financial riskmanagement systems for EU banks. This research proposes an en-semble method based on majority voting (Hard Voting Classifier)of deep learning models to detect fraud transaction. ArtificialNeural Network (ANN), Convolution Neural Network (CNN),Recurrent Neural Network (RNN), Long Short-Term Memory(LSTM) and Gated Recurrent Units (GRU) have been used as deeplearning models. First, the most significant features that affect thetype of transaction (fraud or not fraud) have been selected. Afterthat, the ML-DL models were applied. The performance of theproposed approach is tested using a confusion matrix, recall, pre-cision, F-measure and accuracy. The proposed method is testedusing accurate data that consists of 540,099 transactions recordedin Kaggle repository dataset of two days based on European cardholder for September, 2023. The result shows that the RandomForest (RF) model detected anomalies with 99.99% accuracy,F1-score with 1.00, and excellent recall with 99.99%. As a result,the machine learning model based on RF approach shows promiseas a real-time anomaly detection method with high performanceand low computational cost.

• Details
• Contents