Risk-Based Payment Fraud Detection

Payment frauds are a form of intrusion where money is transferred from a victim’s bank account to the bank account of a fraudster. This paper reviews why in practice, it is neither possible nor economical to prevent 100 percent of payment frauds. It therefore becomes important to detect payment frauds and to control their cost. The paper then combines two unique insights into the nature of payment fraud to propose a new risk-based payment fraud detection method. This method does not try to detect individual fraudulent payments but rather seeks to quantify the expected loss from frauds over a given time period. This expected
loss is the risk posed by frauds, and fraud managers only need to intervene if this risk exceeds a maximum acceptable loss threshold. Below this threshold, payment fraud related losses represent a contained risk, which should be viewed as an operating cost just like shoplifting is an operating cost in retail. The paper critically appraises the risk-based method and discusses its applicability in practice.

By: K. Julisch

Published in: RZ3787 in 2010


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to reports@us.ibm.com .