Fraudulent Transaction Detection using HMM
- Pratik Sable
- Anand Ugale
- Ankit Mahajan
Hidden Markov Model, card holder, transaction, flash code, Bio-informatics, Personal Identification Number (PIN).
as comparing to both online as well as offline Transaction most popular mode of payment is online Transaction, so chances of fraudulent transaction is also increases. Fraudulent transactions are like stolen card, Hack account, lost card, legitimate attack etc. In existing system, fraud is detected after fraudulent transaction performed. In this paper, by using Hidden Markov Model (HMM) we can model the operation in credit card transaction processing to detection of frauds. In this paper, we model the sequence of operations in credit card transaction processing using a Hidden Markov Model (HMM) and show how it can be used for the detection of frauds. 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. We present detailed experimental results to show the effectiveness of our approach and compare it with other techniques.
Pratik Sable, Anand Ugale, Ankit Mahajan. "Fraudulent Transaction Detection using HMM".INTERNATIONAL JOURNAL OF ENGINEERING DEVELOPMENT AND RESEARCH ISSN:2321-9939, Vol.2, Issue 1, pp.913-916, URL :https://rjwave.org/ijedr/papers/IJEDR1401164.pdf
Volume 2 Issue 1
Pages. 913-916
