|Project Description: ||In the current days, with the rapid progression in the e-commerce technology, the usage of credit cards has increased radically due to its varied benefits. The mode of payment through credit card has made people’s life easy for both online and ordinary purchases and thus widespread. This enormous usage of credit card leads to different frauds [Edwin 2011]. In this paper, an enhanced form of the existing model is introduced wherein the sequence of operations in credit card transactions are reproduced, processing using a Hidden Markov Model (HMM) and is demonstrate how it can be used for the detection of frauds in credit cards.
The enhanced form of typical HMM is primarily trained with the standard procedures of a cardholder. If an incoming credit card transaction is not approved by the trained HMM with adequately high probability, it is considered to be fraudulent. During this process, it is also ensured that legitimate transactions are not rejected [Srivatsa 2008]. Through this paper, detailed experimental results are presented to illustrate the effectiveness of the approach and also compare it with other existing models that are available in the literature.