Insurers Tackle A Tough Enemy

As director of MetLife Auto & Home's special investigations unit, John Sargent knows that eliminating fraud is an unachievable goal. But that hasn't stopped his company or other industry leaders from trying."Our goal is to pay what we owe, and not a penny more or a penny less," Sargent says. "The more efficient we are at identifying and preventing fraud, the better we can be at writing business at a more competitive rate."

Industry leaders like Sargent and David Rioux lead teams of trained professionals who are taking on an enemy that steals an estimated $30 billion a year from property/casualty insurers. They believe technology gives them a fighting chance.

"Fraud technology can significantly help in the identification and investigation of fraud," says Rioux, assistant vice president and manager of security and investigative services at Erie Insurance Group, Erie, Pa.

"But where the rubber meets the road is with skilled and talented fraud investigators backed by specialty support services such as data analysts and information resources."

The industry needs more companies that share Rioux and Sargent's vision because collectively, criminals are picking insurers' pockets clean. When you add up the cost of all forms of fraud, including health care and workers' comp, insurers are being bilked to the tune of $100 billion a year.

Fraud is a complex crime perpetrated by skilled individuals and organized crime rings. They send "test" claims to learn how carriers investigate accidents or flag fraudulent claims. They oftentimes have inside help. They even surf the 'Net for articles and information on successful fraud prosecution to identify the carriers that uncovered the schemes.

And, just like the bank robbers of the Old West, they ambush those carriers that don't have sophisticated anti-fraud programs. Evidence suggests they avoid companies that are known to fight fraud aggressively.

"Individuals involved in fraud rings commit fraud for a living, and they are fully aware of which companies have good fraud-fighting programs and which companies don't," says J. Russell Kesler, a regional director of investigative services for St. Paul Travelers Cos., St. Paul, Minn. "I have had people tell me directly that they avoid us because of our efforts."

Insurance fraud is a crime like no other in that it extends across all ethnic groups, all income and education levels, and all geographic areas of the nation, says Dennis Jay, executive director of the Coalition Against Insurance Fraud. The most prevalent fraud schemes perpetrated by fraud rings, such as staged auto accidents and health care billing schemes, typically involve a group of individuals acting in tandem to bilk insurers.

As an example, Russian groups are actively involved in phantom billing to health insurers, Jay explains. "They will research how a billing service operates, and then send out 1 million fake bills. Even if 1% or 2% get paid, it can add up to millions of dollars in a short period of time."

The tactics used by organized rings are indeed stealthy. Oftentimes, such schemes involve individuals employed at an insurer who understands the carrier's fraud detection methods and prosecution of cases.

Also, the hit-and-run tactics used by fraud rings frustrate insurers. Crime rings cook up a scheme and execute their plan, and by the time the red flags start popping up in insurers' fraud-fighting units, the ring has vanished.

"Fraud is being committed by loosely knit networks around the United States," Jay says. "They appear and then disappear, frustrating insurers and law enforcement officials."

Health care fraud is becoming more insidious because of the involvement of physicians and other health care providers, industry observers say. In the past, many of the health care schemes involved billing for services that were not rendered. Now, it involves expensive, medically unnecessary surgeries.

"What's happening now is physicians are paying patients $5,000 or $10,000 to undergo a serious surgical procedure when there's in fact no need for the procedure," says Andrea Allman, director of health care operations and product management for Fair Isaac Corp, a Minneapolis-provider of fraud management technology.

These rent-a-patient schemes target new immigrants who have good jobs and good health insurance. Some of the patients have multiple surgeries, each billed in the hundreds of thousands of dollars.

St. Paul Travelers' Kesler believes that to successfully fight fraud, insurers need the proper balance of trained professionals and technology. And they need organizational commitment to fight the good fight.

"The most important aspect of a fraud fighting game plan is the commitment from everyone in the organization, from the executive level down to the claims handlers," he says.

St. Paul Travelers has armed its claims handlers and fraud investigators with such technologies as predictive modeling software, link analysis and data mining tools.

The carrier also is committed to providing training and other resources to sharpen employees' fraud-fighting skills. And it's joining other organizations to raise public awareness about insurance fraud.

But given the size, scale and sophistication of fraud, experts say the industry needs to do better. They say more carriers need to adopt fraud technologies, hire experienced claims handlers and investigators, and share more data to uncover fraud linkages.

"I don't think that insurers can scale their SIU and other resources to meet the needs of what's out there today," says Michael Lucarini, a partner in the insurance practice at Accenture, Bermuda. "With the technologies to improve the identification of fraud upfront and with the improvements in the quality of the referrals to the SIU, carriers need to right-size their staffs."

Most carriers need to increase their SIU staffing levels, the Coalition's Jay concurs. "Over the last three years, hiring of SIU investigators has been relatively flat," he says. "There haven't been any drastic cuts, but companies that are adding premium volume aren't adding any staff."

Throwing more staff at the problem won't solve the fraud puzzle, experts say. What carriers need to do is come up with the right mix of people and technology.

Five years ago, when carriers first became serious about implementing, fraud technology, there was the belief that the technology would reduce staffing levels for claims handlers or fraud investigators. Erie's Rioux says the opposite is true.

"If you have the right business practices and business processes in place, you should experience a greater need for human resources," he says.

Long-term goals

Back in 2000, when MetLife Auto & Home set out to optimize the performance of its SIU, Sargent and others discussed the company's long-term goals and service objectives and realized that there is only so much staff that carrier could commit to the problem. "We determined that we were adequately staffed," he explains.

That's when Sargent and the company's IT team turned their attention to identifying how technology could enhance fraud detection and investigation efforts. In 2001, Computer Sciences Corp. (CSC), El Segundo, Calif., approached MetLife Auto & Home to discuss a product called Fraud Investigator, which could detect abnormal data patterns-such as ZIP codes and areas codes that don't match, or variations in phone number and VINs-for claims currently in the carrier's claims management system.

Sargent calls the technology reactive because it identifies claims that in most cases have been approved. What he wanted was technology that could flag fraud before the checks were mailed.

MetLife Auto & Home and CSC spent "hundreds of hours" to build the business rules and data fields used to analyze claims and flag suspicious information. Examples of business rules include the amount of time between the date a policy took effect and a claim was filed, the severity of injuries resulting from accidents, the number of occupants in an automobile, and subjective injuries such as soft-tissue injuries.

The team also developed a search engine that would enable investigators to import data from internal and external databases to check on the legitimacy of a medical provider, or query the National Insurance Crime Bureau's Questionable Claims database to see if other NICB members reported similar suspicious claims.

The resulting product, which is now called Fraud Evaluator, went live in February 2003. The solution worked so well that Sargent had to increase staffing to analyze the large number of claims being flagged. He now oversees an SIU staff of 85 that includes 60 investigators and a 10-member analyst team. The analysts examine flagged claims before they're sent to investigators, and they work with claims handlers to gather additional information, such as police reports of accidents.

The results are impressive. Last year, 26% of claims referrals to MetLife Auto & Home's special investigation unit (SIU) were the direct result of claims that were flagged by the carrier's new fraud detection software. Furthermore all referrals to the SIU rose 40%. MetLife declined to provide information on the number of claims that were flagged last year and the number investigated.

Technology is "another tool in our toolbox to aggressively fight fraudulent claims, Sargent says. "You need someone to swing the hammer. We still have significant field investigators and analyst teams to improve the results. If you're only doing one thing, you're not doing what you can and what you should be doing."

Erie's High-Tech Game Plan Starts With Succinct Business Strategy

At Erie Insurance Group, the foundation for fighting fraud is a business strategy that defines objectives, quantifiable goals, and tactical and operational plans: What is the company trying to accomplish? Does the company have enough resources to react to instances of fraud? How is Erie going to get better referrals to its special investigations unit and become more proactive in identifying fraud?

"Erie is keenly aware that our experienced people--our claims adjusters, field investigators, intelligence analysts and information specialists--coupled with our use of fraud detection technology and investigation tools, have made our anti-fraud program so successful," says David Rioux, assistant vice president and manager, corporate security and investigative services for Erie Insurance Group, Erie, Pa.

Rioux, who oversees a group of more than 50 investigators, intelligence analysts and information researchers, believes that technology enables his staff to be more effective and efficient at the work they do. The process starts with a predictive modeling product called FraudFocus developed by Magnify Inc., Chicago. Every day, all Erie claims are scored using a combination of the company's historical data and industry indicators. Suspicious claims are red-flagged and referred to field adjusters. If the claim warrants further investigation, it is sent to fraud investigators.

Erie augments the predictive modeling software with fraud alert notices from the National Insurance Crime Bureau (NICB), a Palos Hills, Ill.-based organization that includes 1,000 insurance companies and law enforcement agencies nationwide. Last year, the group issued 817 reports, called ForeWarn Alerts, that include such information as recent scams the NICB is aware of, status dispositions on NICB cases involving adjudication, requests to insurers to review claims targeting specific types of alleged criminal activity, and law enforcement alerts.

The NICB data is combined with information gathered by Erie's own investigations to create an intelligence watch list. The company's intelligence analysts use data mining software called NetMap for Claims developed by Insurance Services Office Inc. (ISO), Jersey City, N.J., to identify trends, patterns and relationships that are unseen to the eye. The data-mining tool also queries Erie's repository representing five years of claims data to check names, addresses, phone numbers and other identifying information.

Erie also imports ISO ClaimSearch data, a repository of 412 million claims representing 10 years of insurance data, to determine if a person or entity has been flagged for fraudulent activity. Once the company is able to identify its exposure to fraud, the case is referred to a field investigator and the information is sent to the NICB.

Rioux, who worked in law enforcement and had 15 years of experience in field investigation and fraud management before joining Erie in 2001, created the company's case intelligence unit. The first person he hired was a government intelligence officer with experience in terrorism, drug trafficking and military investigations. The second hire was a person who was proficient in using data mining software.

"The analyst component is relatively new to insurance fraud investigations," Rioux says. "The job is to collate information, rule out false-positives and support the field investigators."

The process has worked well for Erie. In one case, Erie received an NICB alert about a medical clinic in New York City that was suspected of billing insurers for durable medical equipment that was assigned to patients but not actually delivered.

Rioux says the company would have had a difficult time quantifying Erie's exposure if it had to manually pull billing records and determine if the clinic had billed the insurer for the equipment.

"Within a few hours of receiving the NICB notice, we queried the system and pulled a good number of claims to determine if we were we billed for the durable medical equipment," he says. "We quickly determined the amount that we paid, identified all of the associated entities such as chiropractors, and packaged the information to our investigator in New York-complete with graphical diagrams and charts."

All of the work that would have taken weeks or months was completed within hours and amounted to more than $200,000 in false claims.

The investment in people and technology has paid off handsomely for Erie. Last year, the company's fraud investigation unit conducted nearly 3,500 investigations, which was 4% higher than a year earlier-and that's despite a 12% drop in claims. In the first six months that the system was operating in 2003, referrals to the SIU rose 28%.

Furthermore, the predictive modeling software flagged 25% of the referrals to the SIU. And those claims reached investigators more quickly than claims that were processed manually. The quality of the referral--a measure indicating an adjuster's ability to articulate the specific reasons why a claim is being referred to the SIU--improved to 95% of claims.

"One of the more interesting aspects of fraud investigations is that your success rate improves the faster a case gets referred to investigators," Rioux notes. Among the 25% of claims that were flagged, the average number of days lapsed from the claim report date was 88 days, and for all other referrals it was 163 days.

Erie had projected a return on its investment of $2 million to $4 million annually in additional claims loss impact over its pre-implementation efforts. (Loss impact is the total claims payments not paid due to alleged claims fraud.) In its first full year of production, Erie realized a loss impact of $5 million, or a 31% improvement over its fraud mitigation results in 2003.

"It's unrealistic to completely eradicate fraud, but you have the potential to make a difference and protect the policyholder," Rioux says. "We take fraud seriously, because it can erode your competitive position. And our moral and ethical beliefs are that you cannot pass the cost on to consumers."

FRAUD FACTS

  • Fraud costs: $85 billion to $120 billion annually
  • Percentage of P&C carriers that have SIUs: 90%
  • NICB members: More than 1,000 property/casualty insurers
  • Number of ForeWarn alerts issued in 2004 by NICB: 817
  • Number of claims in ISO ClaimSearch database: 412 million
  • Number of new claims added to ClaimSearch: 175,000 a day
  • Number of investigation queries to ClaimSearch: 60,000 a day
  • Number of state fraud bureaus: 43
  • Number of cases bureaus refer to prosecutors: 99,000 (2002)
  • Number of cases investigated by law enforcement: 33,000 (2002)
  • Insurance fraud convictions: 2,535 (2002)

Sources: Coalition Against Insurance Fraud, Insurance Information Institute, ISO and the National Insurance Crime Bureau

For reprint and licensing requests for this article, click here.
Claims Data security Policy adminstration Security risk
MORE FROM DIGITAL INSURANCE