Credit Card Fraud Detection Using Neural Network

The payment card industry has grown rapidly the last few years. Companies and institutions move parts of their business, or the entire business, towards online services providing e-commerce, information and communication services for the purpose of allowing their customers better efficiency and accessibility. Regardless of location, consumers can make the same purchases as they previously did " over the desk ". The evolution is a big step forward for the efficiency, accessibility and profitability point of view but it also has some drawbacks. The evolution is accompanied with a greater vulnerability to threats. The problem with making business through the Internet lies in the fact that neither the card nor the cardholder needs to be present at the point-of-sale. It is therefore impossible for the merchant to check whether the customer is the genuine cardholder or not. Payment card fraud has become a serious problem throughout the world. Companies and institutions loose huge amounts annually due to fraud and fraudsters continuously seek new ways to commit illegal actions. The good news is that fraud tends to be perpetrated to certain patterns and that it is possible to detect such patterns, and hence fraud. In this paper we will try to detect fraudulent transaction through the neural network along with the genetic algorithm. As we will see that artificial neural network when trained properly can work as a human brain, though it is impossible for the artificial neural network to imitate the human brain to the extent at which brain work, yet neural network and brain, depend for there working on the neurons, which is the small functional unit in brain as well as ANN. Genetic algorithm are used for making the decision about the network topology, number of hidden layers, number of nodes that will be used in the design of neural network for our problem of credit card fraud detection. For the learning purpose of artificial neural network we will use supervised learning feed forward back propagation algorithm. Finally we will see what future work can be done in making fraud detection. I. INTRODUCTION Credit card fraud Credit card fraud can be defined as " Unauthorized account activity by a person for which the account was not intended. Operationally, this is an event for which action can be taken to stop the abuse in progress and incorporate risk management practices to protect against similar actions in the future ". …