Fraud has long been a significant problem for the insuranceindustry — actually since the very beginning of insuranceat Lloyd's coffee house.

The CoalitionAgainst Insurance Fraud indicates that 5-10 percent of claimscosts are related to fraud, with over 30 percent of insurersreporting as much as 20 percent of claims costs being related tofraud.

Fraud is a lucrative business for fraudsters, and perpetrating fraud becomes more creative everyday. I'm pretty certain that most heads of SpecialInvestigations Units (SIU) feel that "fraudster" should be a jobcategory within the Department of Labor … the focus on committingfraud is so relentless by some, it is almost a profession!

Related: 8 tools for using social media to fight insurancefraud

In my insurer career, I was a technical advisor to an SIU. Ihave always felt that was probably the best job assignment I everhad. The investigators were all ex-law enforcement — bigcity police officers and State Troopers with some FBI agents thrownin for good measure. They told the best stories about chasing downbad guys! Underlying it all, however, was frustration. Detectingfraud is hard. Finding the fraudsters and prosecuting them, evenharder.

Getting out in front of fraud

Current estimates are that only 1.5 percent of cases areprosecuted. Unfortunately, some insurers have an attitude aboutfraud that borders on: "It's just a cost of doing business."However, that attitude cannot persist in today's businessenvironment where every dollar of claims costs must be acutelymanaged to maximize very thin bottom-line margins.

The recent SMA research brief, Fighting Fraud with Advanced Technology: Detection,Mitigation, and Prevention, recounts the historical and currentpath of fraud detection, starting with the "gut feel" of seasonedclaims adjustors. Then, along came business rules which allowed foruniformity and some automation. Today, predictive analytics andlink analysis are the leading solutions for fraud detection. Inparticular, link analysis is an effective way to find fraud ringsthat attempt to hide within large claims volumes using technologyto change their personas.

Ironically, the new reality for insurers is that the moredigital they become, the easier it is for fraudsters to hide andreinvent themselves. Fully automated, online new businessapplications allow fraudsters to gain access to coverage.Electronic claims submissions permit individuals, includingunscrupulous doctors and lawyers, to submit "documentation" thatpayments are warranted. No insurer is going to stop their digitalinitiatives because of this. However, insurers need to augmentbusiness rules, predictive analytics, and link analysis withemerging technologies in the fight against fraud.

Related: 9 factors impacting claims in 2017

Telematics can assist adjusters, for example, in determining ifa vehicle in question was in the location alleged at the time ofthe loss, or if the reported injuries actually equate to the crashdetails or appear to be fabricated. Telematics aren't just forrating! Wearables can do the same thing relative to individualworkers. Could a severe injury claimed from a fall actually haveoccurred given the dynamics of the fall?

Big data, emerging tech

Big data and emerging technologies such as artificialintelligence (AI), behavior science, and behavioral analytics holdthe promise of allowing insurers to get out in front of fraud. Theclear problem that SIU investigators have, even with link analysisand predictive analytics, and certainly withbusiness rules, is that they are always chasing the fraudstersafter they have gotten claim payments. It's true that predictiveanalytics and link analysis can minimize the number of fraudulentpayments the fraudster obtains, but, the fact is that the bad guysget themselves into the payment que and then the alerts and flagsgo up.

Big data, AI, and behavior analytics have the great potential tocut off the fraudsters before they get a claim payment. And, wedon't know what we don't know when it comes to AI and behavioralanalysis — whole new worlds of fraud fighting capabilitiesmay arise out of new insights.

I would dearly love to reconnect with the SIU team I worked with"back in the day." It would be amazing for them to see what currentpredictive analytics and link analysis in an automated fashion cando, where they once applied sweat and elbow grease to accomplishwhatever they could with precious few positive results … and tobrainstorm outcomes aided by telematics, wearables, AI, andbehavior analysis. The most amazing thing for them to witness isthat current and future fraud-related technology investmentscombined with the honed skills of SIU investigators can generatesignificant ROI and change the attitudes about fraud being anothercost of doing business!

Karen Pauli is a principal atBoston-based SMA,independent advisors to insurers and InsurTech solutionproviders. Email her at [email protected].This article first appeared on StrategyMeetsAction.com and isreprinted here with theirpermission. Opinions are the author'sown.