Cost Sensitive Modeling of Credit Card Fraud Detection Using a Hybrid Genetic Algorithm- Neural Network Strategy

This paper intends to develop a credit card fraud detection (CCFD) model based on Artificial Neural Networks (ANN). Because of the unbalanced nature of the data (Fraud and Non-Fraud cases), the detection of fraudulent transactions is a difficult goal to achieve. To deal with the problem of imbalanced data, Meta Cost procedure is added. Applying Genetic Algorithm (GA) to the Neural Network (NN) for topology automation design results in improved performance. The proposed model is based on misuse detection approach. Compared to the model based on Artificial Immune System (AIS), this hybrid model showed cost saving and increased detection rate. Data of this study is taken from a real transactional data provided by a big Brazilian bank

Keywords:

Credit Card Fraud Detection , Imbalanced Data , Artificial Neural Network , Meta Cost Procedure