Credit/Debit Card Fraud Detection System Using Hidden Markov

Abstract

The use of credit and debit card has been increased day by day. So the financial fraud or the fraudulent transaction has also increased day by day in today’s world because of development of modern technology. With the help of these cards we can make both online and offline payment easily. For online transaction it uses virtual card and for offline transaction it uses physical card. In today’s world, credit and debit card provides cashless shopping at every shop. In this fraud detection system (FDS), when a fraudulent transaction is going to be done, it will be detected by this system. A fraud can be detected using Hidden Markov Model (HMM) during transaction. In this project, the sequence of operations in credit card transaction processing system using a Hidden Markov Model and show how it can be used for the detection of fraud. An HMM is initially trained with the normal behavior of a 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 the same time, we try to ensure that genuine transactions are not rejected.