Staying a Step Ahead of Fraud

The perpetrators of fraud change tactics faster than conventional methods of detection can track. Predictive analytics, authentication and rules engines will help detect and fight crime before the losses mount.


John Sargent
Director, Special Investigative Unit, MetLife Auto & Home

What's the most difficult type of fraud to detect?

It's very difficult to detect someone who is that one-time opportunist, who decides to claim damage [fraudulently]. You want to err on the side of believing your insured.

What are the limits of antifraud technology today?

We look at it as truly just a tool. It brings to light those things that need to be looked at, but the system doesn't tell you if something is fraud.

What else would help you fight fraud?

Additional access to public record data might help improve our results. We also think there should be better sharing of suspicious claim data to help the entire industry. If companies were more forthcoming with their suspicious claim data, everyone would benefit.

Editor's Choice
Brian T. Horowitz, Contributing Reporter
Samuel Greengard, Contributing Reporter
Nathan Eddy, Freelance Writer
Brandon Taylor, Digital Editorial Program Manager
Jessica Davis, Senior Editor
Cynthia Harvey, Freelance Journalist, InformationWeek
Sara Peters, Editor-in-Chief, InformationWeek / Network Computing