Survey on Credit Card Fraud Detection Using Different Data Mining Techniques

In today's world of e-commerce, credit card payment is the most popular and most important mean of payment due to fast technology. As the usage of credit card has increased the number of fraud transaction is also increasing. Credit card fraud is very serious and growing problem throughout the world. This paper represents the survey of various fraud detection techniques through which fraud can be detected. Although there are serious fraud detection technology exits based on data mining, knowledge discovery but they are not capable to detect the fraud at a time when fraudulent transaction are in progress so two techniques Neural Network and Hidden Markov Model(HMM) are capable to detect the fraudulent transaction is in progress. HMM categorizes card holder profile as low, medium, and high spending on their spending behavior. A set of probability is assigned to each cardholder for amount of transaction. The amount of incoming transaction is matched with cardholder previous transaction, if it is justified a predefined threshold value then a transaction is considered as a legitimate else it is considered as a fraud.