期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2014
卷号：5
期号：3
页码：4684-4691
出版社：TechScience Publications
摘要：In the current retail merchandise surroundings, electronic commerce has gained lots of attention and additionally provides spontaneous transactions. Using Ecommerce individuals do their monetary dealing on-line like on-line shopping etc. In e-commerce, card payment mode has become the foremost vital suggests of payment because of quick development in information technology around the world. Because the usage of card payment mode has increased within the last decade, the magnitude of dishonest practices is additionally increasing each year. In-spite of every tries to stop fraud, it carries on to be a serious threat to trade and government. Historically, organizations have been targeted fraud, interference instead of detection, to combat fraud. During this paper, we offer implementation and result analysis of a system that is employed to sight fraud in on-line dealings. The system relies on the Hybrid Markov Model that may be a combination of Hidden Markov Model, Bayesian Classifier and bio-metric method to sight fraud a lot of expeditiously than all previous planned system of fraud detection. The proposed system models the sequence of operations in Card transaction process employing a Hidden Markov Model (HMM) and social status of the cardboard holder using Bayesian classifier therefore showing how it is used for the detection of frauds. The performance of our proposed system is better than all the previously proposed system because in our proposed system we are using OTP and Biometric Authentication which reduces the possibility of the occurrence of the fraud in credit card transaction.
