Credit Card Fraud Detection Based on Hyperparameters Optimization Using the Differential Evolution
Mohammed Tayebi, Said El Kafhali
Abstract
Due to the emigration of world business to the internet, credit cards have become a tool for payments for both online and outline purchases. However, fraudsters try to attack those systems using various techniques, and credit card fraud has become dangerous. To secure credit cards, different methods are proposed in the academic paper based on artificial intelligence. The proposed solution in this paper aims at combining the robustness of three methods: the differential evolution algorithm (DE) for selecting the best hyperparameters, a resampling technique for handling imbalanced data issues, and the XGBoost technique for classification. Finally, the fraudulent transactions are classified using the optimized XGBoost algorithm. The proposed solution is evaluated using two real-world datasets: the European dataset and the UCI dataset. The evaluation in terms of accuracy, sensitivity, specificity, precision, and F-measure shows the ability and the superiority of the proposed approach in comparison with the state-of-the-art machine learning models.