Generative Adversarial Networks-Based Novel Approach for Fraud Detection for the European Cardholders 2013 Dataset

Credit card use poses a significant security issue on a global scale, with rule-based algorithms and traditional anomaly detection being two of the most often used methods. However, they are resource-intensive, time-consuming, and erroneous. Given fewer instances than legal payments, the dataset imbalance has become a serious issue. On the other hand, the generative technique is considered an effective way to rebalance the imbalanced class issue, as this technique balances both minority and majority classes before the training. In a more recent period, GAN is considered one of the most popular data generative techniques, as it is used in significant data settings. Hence, the research under study explores a classification system to detect fraudulent credit card transactions that are being trained using the European Cardholders 2013 dataset. It has 30 features, 28 of which are hidden due to sensitive information. Fraud activity accounts for less than 1% of the entire transaction volume of $284807. Additionally, GANs is a generative model based on game theory, in which a generator G and a discriminator D compete with one another. The generator's goal is to make the discriminator uncertain. Distinguishing between instances from the generator and those from the original dataset is the discriminator's goal, and we can increase classifiers' discriminating strength by training GANs on a set of fraudulent credit card transactions. According to the outcome, our model outperformed the earlier experiments with an AUC score of 0.999. Additionally, it creates artificial data using GANs, enabling the production of a sizable volume of high-quality data. In terms of innovation and performance, this technique substantially improves over earlier research.