Under the Hood: Card Fraud Detection and the Role of Predictive Analytics

Share Article

The hub of the report is fraud detection; stopping fraud 'in-flight'. The use of predictive analystics is at the core of this; building models based on a wide variety of factors to detect anomalous events in a transaction. The science is a fascinating one, applying the principles behind artificial intelligence to solve present day issues. Central to this are neural networks.

Previous Mercator Advisory Group research has investigated the myriad solutions to the problem of authenticating both the cardholder and the merchant in an online environment. But what if the authentication method has successfully been navigated by a fraudster -- what then?

The hub of the report is fraud detection; stopping fraud 'in-flight'. The use of predictive analystics is at the core of this; building models based on a wide variety of factors to detect anomalous events in a transaction. The science is a fascinating one, applying the principles behind artificial intelligence to solve present day issues. Central to this are neural networks.

Nick Holland, Director of the Emerging Technologies Advisory Service and co-author of the report sees the power of fraud detection to be part of a holistic risk management strategy:

"It's safe to assume that fraud will never go away and that we will see ever more dubious and audacious fraud schemes as new electronic payment paradigms such as contactless cards and mobile payments come of age. But the combination of preventative and detective tools coupled with intelligent human decisioning goes a long way towards 'cramping the fraudster's style.'"

Hightlights of the report include:

1. Coverage of the major sources of fraud and their individual characteristics

2. A section on the way that fraud evolves including a case study on 'phishing'

3. Analysis of fraud countermeasures for prevention and detection in both the online and physical world

4. In-depth explaination of the scientific principles behind predictive analytic solutions, with specific reference to neural networks

5. Examples of fraud detection solutions from some of the major providers including ACI Worldwide, Fair Isaac, Retail Decisions(ReD), ID Analytics and CyberSource, including schematics of fraud detection architecture.

The report contains 13 exhibits and is 31 pages.

Members of Mercator Advisory Group have access to these reports as well as the upcoming research for the year ahead, presentations, analyst access and other membership benefits. Please visit us online at http://www.mercatoradvisorygroup.com.

For more information call Mercator Advisory Group's main line: 508-845-5400 or send e-mail to info@mercatoradvisorygroup.com.

# # #

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Robert Misasi, President & CEO
Visit website