Credit Card Fraud Detection System Using Hidde Markov Model
CHAPTER ONE 1.0 INTRODUCTION
In day to day life credit cards are used for purchasing goods and services by the help of virtual card for online transaction or physical card for offline transaction. In physical transaction, Credit cards will insert into payment machine at merchant shop to purchase goods. Tracing fraudulent transactions in this mode may not be possible because the attacker already steal the credit card. The credit card company may go in financial loss if loss of credit card is not realized by credit card holder. In online payment mode, attackers need only little information for doing fraudulent transaction (secure code, card number, expiration date etc.). In this purchase method, mainly transactions will be done through the Internet or telephone. Small transactions are generally undergo less verification, and are less likely to be checked by either the card issuer or the merchant. Card issuers must take more precaution against fraud detection and financial losses. Credit card fraud cases are increasing every year. In 2008, number of fraudulent through credit card had increased by 30 percent because of various ambiguities in issuing and managing credit cards. Credit card fraudulent is approximately 1.2% of the total transaction amount, although it is not small amount as compare to total transaction amount which is in trillions of dollars in 2007[ 2-4] . Hidden Markov Model will be helpful to find out the fraudulent transaction by using spending profiles of user. It works on the user spending profiles which can be divided into major three types such as 1) Lower profile; 2) Middle profile; and 3) Higher profile. For every credit card, the spending profile is different, so it can figure out an inconsistency of user profile and try to find fraudulent transaction. It keeps record of spending profile of the card holder by both way, either offline or online. Thus analysis of purchased commodities of cardholder will be a useful tool in fraud detection system
In day to day life credit cards are used for purchasing goods and services by the help of virtual card for online transaction or physical card for offline transaction. In physical transaction, Credit cards will insert into payment machine at merchant shop to purchase goods. Tracing fraudulent transactions in this mode may not be possible because the attacker already steal the credit card. The credit card company may go in financial loss if loss of credit card is not realized by credit card holder. In online payment mode, attackers need only little information for doing fraudulent transaction (secure code, card number, expiration date etc.). In this purchase method, mainly transactions will be done through the Internet or telephone. Small transactions are generally undergo less verification, and are less likely to be checked by either the card issuer or the merchant. Card issuers must take more precaution against fraud detection and financial losses. Credit card fraud cases are increasing every year. In 2008, number of fraudulent through credit card had increased by 30 percent because of various ambiguities in issuing and managing credit cards. Credit card fraudulent is approximately 1.2% of the total transaction amount, although it is not small amount as compare to total transaction amount which is in trillions of dollars in 2007[ 2-4] . Hidden Markov Model will be helpful to find out the fraudulent transaction by using spending profiles of user. It works on the user spending profiles which can be divided into major three types such as 1) Lower profile; 2) Middle profile; and 3) Higher profile. For every credit card, the spending profile is different, so it can figure out an inconsistency of user profile and try to find fraudulent transaction. It keeps record of spending profile of the card holder by both way, either offline or online. Thus analysis of purchased commodities of cardholder will be a useful tool in fraud detection system
References: http://en.wikipedia.org/wiki/Adobe_Dreamweaver[Nov. 22, 2010] [22] Jay Greenspan and Brad Bulger