International Journal of Advance Research and Innovation (IJARI)
As online banking becomes the most popular mode of payment for both online as well as internet based transaction, cases of fraud associated with it are also rising. In this paper, the authors model the sequence of operations in internet banking transaction processing using a Hidden Markov Model (HMM) and showing how it can be used for the detection of frauds. If an incoming online banking transaction is not accepted by the trained HMM with sufficiently high probability, it is considered to be fraudulent. At the same time, they will try to ensure that genuine transactions are not rejected.