Integrating Artificial Neural Networks and Support Vector Machines Machine Learning Algorithms for Advanced Credit Card Fraud Detection

In recent years, rising fraudulent activities have inflicted substantial financial losses across industries, with credit card fraud detection posing persistent challenges due to the diverse techniques employed by fraudsters. This study, an ex-tension of prior research (Ndama, Oussama, and El Mokhtar En-Naimi. “Credit Card Fraud Detection Using SVM, Decision Tree and Random Forest Supervised Machine Learning Algorithms.” International Conference on Big Data and Internet of Things. Cham: Springer International Publishing, 2022; Oussama Ndama and El Mokhtar En-Naimi. 2023. Optimisation and Resampling methods for Handling Imbalanced Datasets in Credit Card Fraud Detection using Artificial Neural Networks. In Proceedings of the 6th International Conference on Networking, Intelligent Systems & Security (NISS ‘23). Association for Computing Machinery, New York, NY, USA, Article 23, 1–10. https://doi.org/10.1145/3607720.3607745 ), addresses the issue of imbalanced datasets in fraud detection by leveraging the Synthetic Minority Over-sampling Technique (SMOTE). The research explores hybrid methodologies by integrating artificial neural networks with Support Vector Machines (SVM) using various kernels, building upon the initial study. Evaluating 284,807 anonymized transactions, the study emphasizes the comparative performance of the hybrid approach with SMOTE, providing insights into its effectiveness in mitigating challenges associated with imbalanced datasets in credit card fraud detection.