Credit Card Fraud Detection using Big Data Analytics

Abstract

Banking and financial industries are facing severe challenges in the form of fraudulent transactions. Credit card fraud is one example of them. In order to detect credit card fraud, we employed one-class classification approach in big data paradigm. We implemented a hybrid architecture of Particle Swarm Optimization and Auto-Associative Neural Network for one-class classification in Spark computational framework. In this paper, we implemented parallelization of the auto-associative neural network in the hybrid architecture.