• SELVANANDHAM S
• L RAHUNATHAN

Fraud detection is generally viewed as a data mining classification problem, where the objective is to correctly classify the credit card transactions as legitimate or fraudulent. Even though fraud detection has a long history, not that much study has appeared in this area. The reason is the unavailability of real world data on which researchers can perform results since banks are not ready to reveal their sensitive user transaction data due to privacy reasons. Moreover, they used to change the field names so that the researcher would not get any idea about actual fields. Card fraud begins either with the theft of the physical card or with the compromise of data associated with the account, including the card account number or other information that would routinely and necessarily be available to a merchant during a legitimate transaction. Stolen cards can be reported quickly by cardholders, but a compromised account can be hoarded by a thief for weeks or months before any fraudulent use, making it difficult to identify the source of the compromise. The cardholder may not discover fraudulent use until receiving a billing statement, which may be delivered infrequently. In existing system, Hidden Markov Model is the statistical tools for engineer and scientists to solve various problems. In this paper, it is shown that credit card fraud can be detected using Hidden Markov Model during transactions. Hidden Markov Model helps to obtain a high fraud coverage combined with a low false alarm rate. The proposed fraud detection model (Fraud Miner) during the training phase, legal transaction pattern and fraud transaction pattern of each user are created from their legal transactions and fraud transactions, respectively, by using Apriori algorithm frequent mining. Then during the testing phase, the matching algorithm detects to which pattern the incoming transaction matches more. If the incoming transaction is matching more with legal pattern of the particular customer, then the algorithm returns “0” (i.e., legal transaction) and if the incoming transaction is matching more with fraud pattern of that user, then the algorithm returns “1” (i.e., fraudulent transaction)

Classification Model, Hidden Markov Model, Fraud Miner, Apriori Algorithm, SVM classification

"Effective Credit Card Fraud Detection Using Self Organization Mapping with SVM Model ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.570-578, March-2019, Available :http://www.jetir.org/papers/JETIR1903578.pdf

"Effective Credit Card Fraud Detection Using Self Organization Mapping with SVM Model ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp570-578, March-2019, Available at : http://www.jetir.org/papers/JETIR1903578.pdf