Career Center Powered by GreatInsuranceJobs.com
NU Online News Service, Aug. 18, 12:02 p.m. EDT
ORLANDO, FLA.—A trio of experts here explaining predictive modeling said that while it won’t replace knowledgeable insurance adjusters and underwriters, it is the wave of the future for the workers’ compensation industry.
Their remarks were made during a panel session at the Workers’ Compensation Educational Conference presented by the Florida Workers’ Compensation Institute in partnership with The National Underwriter Company.
Jennifer Tomilin, senior vice president, Zurich North America, said she could not foresee underwriters ever being replaced because “there are areas where we don’t have enough data for predictive modeling.”
But modeling is the future and companies that are “stuck in the mud” and ignore it, “those folks are going to be left behind,” warned Steve Laudermilch, senior manager Deloitte Consulting.
The three panelists, including Kaleb Adams, vice president of Predictive Modeling Specialty Risk Services, outlined a variety of ways in which modeling is used, what data types it employs and what it targets.
Ms. Tomilin said modeling, sometimes called data mining, is an analysis that finds unsuspected relationships that relate to data in novel ways.
For example, in researching a company, the modeler might look at how many employees in a particular ZIP code work from home, and Dunn and Bradstreet ratings.
Some data that is sifted through is ultimately tossed out. She gave an example of an examination of sweet dessert purchases in a certain ZIP code, for a possible link to truck accidents, because eating sugar can cause drowsiness.
She also noted that discriminatory data of the kind once used in redlining is rejected.
The value of predictive models, she said, is that they take “a lot of the subjectivity out” of analysis and eliminate “the gut feel practices.”
Mr. Adams said predictive modeling can serve insurers by, among other things, targeting fraud, identifying claimants who will benefit by treatment from a specialist and helping to “triage claims.”
While he said data from insurers’ underwriting side is not that good, it is voluminous from the claims sector and can be used to provide facts concerning a loss, a worker’s claims history and co-morbidity factors such as obesity.
He said modeling can pin down cases that would benefit from having a special nurse assigned, those that indicate they will involve a large loss and those that need less attention.
Mr. Adams said the system can use text mining to read over notes and identify a fraud situation, a health problem such as morbid obesity or a risk management problem such as a wet floor.
Models that are used, Mr. Laudermilch said, are built by testing the impact of hundreds of variables—such as lifestyle, age, employment history and pharmacy drug use—against closed claims.
The models, he said, will be based on data on injury groups, such as back strains, to identify which are the more serious cases in relation to all the others.
“This is not a replacement for adjusters,” he noted. “The idea is to give them claims they can work on,” accelerating their best practices.
Explaining some of the areas where data is derived, Mr. Laudermilch noted that companies glean it from items such as warrantee forms that customers fill out.
Learning that a person has interests in outdoor pursuits or running for fitness can lead to a conclusion that if injured, “you are probably interested in getting healthy,” he added.