A Survey on GAN Techniques for Data Augmentation to Address the Imbalanced Data Issues in Credit Card Fraud Detection

Data augmentation is an important procedure in deep learning. GAN-based data can be utilized many domains. For instance, the credit card fraud domain, imbalanced dataset problem a major one as number of cases minority compared to legal payments. On other hand, generative techniques are considered effective ways rebalance class issue, these balance both and majority classes before training. In more recent period, Generative Adversarial Networks (GANs) most popular they used big settings. This research aims present survey on using various GAN variants detection domain. this survey, we offer comprehensive summary several peer-reviewed papers synthetic generation for financial sector. addition, includes solutions proposed by different researchers classes. end, work concludes pointing out limitations articles future issues, proposes address problems.