Development of Deep Learning based Intelligent Approach for Credit Card Fraud Detection

Abstract

Credit card fraud (CCF) has long been a major concern of institutions of financial groups and business partners, and it is also a global interest to researchers due to its growing popularity. In order to predict and detect the CCF, machine learning (ML) has proven to be one of the most promising techniques. But, class inequality is one of the main and recurring challenges when dealing with CCF tasks that hinder model performance. To overcome this challenges, a Deep Learning (DL) techniques are used by the researchers. In this research work, an efficient CCF detection (CCFD) system is developed by proposing a hybrid model called Convolutional Neural Network with Recurrent Neural Network (CNN-RNN). In this model, CNN acts as feature extraction for extracting the valuable information of CCF data and long-term dependency features are studied by RNN model. An imbalance problem is solved by Synthetic Minority Over Sampling Technique (SMOTE) technique. An experiment is conducted on European Dataset to validate the performance of CNN-RNN model with existing CNN and RNN model in terms of major parameters. The results proved that CNN-RNN model achieved 95.83% of precision, where CNN achieved 93.63% of precision and RNN achieved 88.50% of precision.