Credit Card Fraud Detection Using Hidden Markov Model
Today's world is Internet world. Now-a-day popularity of E-commerce is increasing tremendously. Using E-commerce people do their financial transaction online like online shopping etc. Most popular mode for online and offline payment is using credit card, use of credit card has dramatically increased. So as credit card is becoming popular mode for online financial transactions, at the same time fraud associated with it are also rising. In this paper Hidden Markov Model (HMM) is used to model the sequence of operation in credit card transaction processing. HMM is trained using Baum-Welch algorithm with normal behaviour of cardholder. If an incoming credit card transaction is not accepted by the trained HMM with sufficiently high probability, it is considered to be fraudulent. At last we will see the performance of this system with the help of True Positive (TP) and False Positive (FP) parameters.