Fraud detection system for the faster payments system

Abstract

A computer-based fraud detection system stores extracts of the payment and other activity of the payer as well as the payee by efficiently profiling their accounts, and also stores extracts of the overall global or segmented payment activities. This profile information is then used to effectively capture fraudulent activity. The fraud detection system accepts messages from the payment processing system or from the associated financial institution, and depending on the nature of the message will update its databases, or assess fraud risk by computing a score, or both. If a score is computed, the higher the score, the greater the likelihood that the transaction is fraudulent. Said score is based on automatically determined risky values of variables and is also be automatically scaled using self-calibrating analytics using the captured profile information. In a typical scenario the fraud detection system client sets a 'threshold score' above which the transactions are considered suspect enough to be investigated further or to trigger a payment decline outright. The solution is suitable for being installed at a financial institution, on the network, or some other institutional participant of the Faster Payments System (FPS), such as an access service provider to the FPS for corporate clients.