Fraud can be subtle and complex. It can be hidden among voluminous amounts of data. New schemes are always emerging. Insurers understand the impact of fraud and consider it a serious problem.Fraud management technology that uses predictive modeling to identify suspicious claims can accurately cull out high-risk claims and label them at the earliest possible moment. It not only makes it practical for insurers to process and close the vast majority of claims faster, it focuses the adjusters review on claims that require the most attention. Lastly, it provides higher quality referrals to investigative units.

"Predictive modeling differs from other types of fraud detection systems in that it enables companies to find fraud activity that is new and emerging, previously undiscovered, complex, or organized schemes," says Ben Friesen, program manager of predictive property and casualty fraud analytics at Fair, Isaac and Co. Inc. "With these solutions, high-risk claims are accurately identified at the earliest possible moment to mitigate losses," adds Friesen. "Predictive modeling makes it practical for insurers to process and close the vast majority of claims faster. Productivity is improved because adjusters are focused on claims that require the most attention, and referrals to investigative units are of high quality."

Software technologies that can detect fraud and other exceptions are the logical cost-saving solutions to a manual approach, according to the software firm. Last year, San Rafael, Calif.-based Fair, Isaac purchased HNC Software Inc., a provider of fraud-fighting technology to the insurance industry (see "Thought-Provoking Technology," June 2002).

Fair, Isaac says its software technology can be used for auto-repair fraud. Although the firm doesn't currently market a product with this application, the same principles that are used to detect other kinds of fraud can be applied to the auto-repair business.

Register or login for access to this item and much more

All Digital Insurance content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access