Credit Card Fraud Detection Using Hidden Markov Model

TLDR

The Internet has become integral to daily life, with most online shoppers using credit cards, leading to a rise in credit‑card fraud. This study proposes using a Hidden Markov Model to model transaction sequences for fraud detection. The HMM is trained on normal cardholder behavior and flags transactions that the model deems unlikely. Experimental results demonstrate the approach’s effectiveness in detecting fraudulent transactions.

Abstract

The Internet has taken its place beside the telephone and the television as an important part of people's lives. Consumers rely on the Internet to shop, bank and invest online. Most online shoppers use credit cards to pay for their purchases. As credit card becomes the most popular mode of payment, cases of fraud associated with it are also increasing. 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 trained with normal behavior of cardholder. If an incoming credit card transaction is not accepted by the HMM with sufficiently high probability, it is considered to be fraudulent. We present detailed experimental results to show the effectiveness of our approach.