Real or Fraudulent? Knowing is Important

Worldwide Industry Marketing Manager for Insurance, IBM


Insurance claims fraud is estimated to account for at least 15 percent of insurance company losses, a cost that impacts the bottom line of every insurer in the industry, and ultimately, consumers as well.

Insurance Bureau of Canada (IBC), Canada’s national insurance industry association for home, car and business insurers, represents 90 percent of the property and casualty insurance market in Canada. IBC provides investigative services to protect the premiums of honest policyholders.

But insurance fraud detection and investigation are constrained by the manual and ad hoc approach employed by the insurance industry. Success with this approach usually depends on the keen eye of a front-line adjuster or a tip from an informant. Consider the following fictional scenario:

It’s 2 a.m. along a deserted stretch of highway. Nobody is present to witness an accident. A car entering the highway has been sideswiped by a car passing in the right lane. The struck car sustains extensive damage while the other car has minor scratches and dents. Three passengers in the struck car claim serious injuries, but the driver is uninjured. There is no police report. Every detail in this account is suspicious, according to existing insurance industry business rules.

car-crash.jpgIn fact, the sideswipe collision was staged and actually occurred a few hours earlier in an abandoned parking lot, then re-enacted on the highway. However, the information needed to prosecute the fraudsters isn’t immediately available. To find it, analysts will need to examine many claims to resolve social networks and associate individuals with suspicious claims.

Investigation reveals that the drivers of both cars shared the same address several years ago under different names and have made numerous claims before, all involving sideswipe collisions. The perpetrators are part of an organized crime ring involving the same individuals working under aliases, using the same body shops and other service providers. Without technology to identify these patterns, manual investigation on a case-by-case basis is slow and labor intensive.

To significantly reduce the number of fraudulent claims it receives, IBC engaged IBM to analyze their claims data in an effort to detect evidence of fraud. The result may be a solution to the problem of identifying insurance fraud in its early stages—a way to quickly and efficiently identify potentially fraudulent claims and link them with the organized crime rings that profit from them.

After looking at existing, limited data for organized fraud provided by IBC from over 233,000 claims from six years, the analysis identified over 2,000 Ontario automobile claims that were potentially fraudulent and had a value of Can$41 million. An extrapolation of that data to estimate the annual impact of just organized fraud on the Ontario automobile insurance industry is approximately Can$200 million. As outlined in the “Ontario Automobile Anti-Fraud Task Force—Status Update,” the potential cost of all types of fraud is conservatively estimated to be as much as Can$770 million—Can$1.6 billion in 2010.

Using analytics technology, IBM was able to quickly verify two criminal fraud rings that IBC had previously identified and investigated over multiple years using manual methods.

With help from the IBM big data platform, insurers will be able to reduce fraud, which can extend from opportunistic exaggerated claims to organized multi-million dollar rings involving staged collisions and dishonest towing companies, repair shops, paralegals and medical clinics.

Learn more about IBM solutions for big data