More and more, insurers are looking to incorporate predictiveanalytics to achieve business results.

"Over the last two years the pace of change has increased," saysSteve Kauderer, partner in Bain & Co.'s Financial Servicespractice in its New York office. "The identification of bothinternal and external data to use in analytics has increased, andthe ability to link and bring disparate groups of informationtogether has grown."

ACUITY's Ed Felchner maintains that having an effectiveanalytics strategy has evolved from competitive advantage just afew years ago to market necessity.

"You have to have at least some capabilities in predictiveanalytics today or you are going to fall behind," says Felchner,ACUITY's vice president of personal lines and marketing. "We'refortunate to not be playing catch-up and to have established afoundation for analytics we can build on to increase competitiveadvantage."

Analytic Goals

Predictive analytics differs from data mining and reportingbecause of its forward-looking objective of predicting outcomes.P&C insurers are using analytics to target many strategicobjectives, but two areas of focus stand out from the rest.

"We see insurers predominantly making investment in underwritingand claims," says Arunashish Majumdar, chief architect and leaderof the insurance practice in North America for TCSconsultancy. 

William Dibble led Infinity Property and Casualty Corp.'snational claims operation until his retirement in 2013,spearheading the company's efforts to implement a real-timepredictive analytics solution to detect potential fraud and improveclaims processes and outcomes. He now serves on the advisory boardof n2uitive, a provider of recorded statement products andservices, and as an independent consultant for insurers, advisingon the use of analytics in claims operations.

"Companies are getting a lot more sophisticated in gathering andanalyzing data and using it to predict claims outcomes and detectfraud," Dibble says. At Infinity, analytics helped the companyimprove its special investigative unit success rate from 60% to90%; however, Dibble stresses that carriers need to continue torefine their analytics to keep ahead in the cat-and-mouse game thatis the insurance fraud fight.

Learn new strategies for properly leveraging data at the19th annual America's Claims Event, June 17-19 in Austin. For moreinformation, click here. Use Code PC360AE & Save$100.

"As carriers get more sophisticated with detecting organizedcrime and connecting the dots to identify groups of people who aregoing into organized fraud, they see that those groups refine theirapproaches to avoid detection. Insurers need to have adaptiveanalytic models and continue to use what they learn to stay a stepahead," Dibble says.

Risk selection and pricing remains a key focus for insurersbecause of its impact in terms of lift. Based on its work withP&C carriers, Bain estimates that companies can improve theircombined ratio by 3 to 5 percentage points and their premium growthby 5%-15% above baseline expectations by using predictive analyticsto actively target high-profit potential customers with attractivepricing and drive the worst risks to competitors.

"We consistently see the best carriers accomplish those goals,"Kauderer says.

"For us, targeting greater precision, being more competitive onnew business, and getting the right price on existing business waswell worth the investment in analytics," says Pat Tures, vicepresident of actuarial at ACUITY.

"Our goal is to have everyone pay what they owe—no more noless—and to not have some customers subsidize others. The moreaccurately you can price, the more fair you will be, and the morecompetitive you will be overall," Felchner says.

ACUITY pursues a "precision pricing" strategy in personal linesthat incorporates different analytic tools and a continuallyevolving array data and information sources. A key factor in thecompany's strategy is the use of AudaExplore's Insight products. In2013, ACUITY began using Property Location Insight (PLI) fromAudaExplore and,in 2014, it began using Auto Location Insight (ALI).

Both PLI and ALI are location-based predictive models that lookat a wide range of variables, including weather, geography,topography, road conditions, traffic volume and infrastructure.Each model creates an account-specific score that accuratelyreflects the probability of loss from fire, theft, liability,weather and other events.

"We can insure two customers living next to each other who havecompletely different scores because of different exposures. Itallows us to rate by peril, and within each peril have very narrowbands of pricing," Felchner says.

For instance, a home adjacent to a commercial area may face ahigher risk of crime than one a few blocks away. Or, vehiclesgaraged at the end of a cul-de-sac could be less susceptible tocollision loss than those parked at the end of the road near theintersection. The result of this analysis is individual risk-basedpricing.

"Years ago we had wide rating bands and perhaps a couple ofhundred pricing points, and the whole universe of risk had to fitin there. Now we have literally billions of possibilities, witheach account developing a unique price that is right for it," saysTures.

Although Felchner says there are several factors behind thecompany's growth in its personal lines division, individualrisk-based pricing has been essential. The company achieved a 32%growth in new business personal lines premium in 2013, is on trackto exceed that in 2014 while running a profitable combinedratio.

Targeting Business Outcomes

In evaluating predictive analytics, companies may be tempted tostart with the data. That's the wrong approach, Majumdar says.

"Start with the business problem," he explains. "What are youtrying to solve? What is the business outcome you want toachieve?"

At Falls Lake National (formerly named Stonewood NationalInsurance Co.), the objective was improving underwriting results.In the years following the onset of the 2008 recession, the insurerbegan to experience significant profitability problems with itsbook of Workers' Compensation business.

"We were a beneficiary of the good times before the recession of2008, but suffered through the bad times after it," says SteveHartman, CEO and president at Falls Lake National.

Those bad times culminated in significant underwriting lossesfrom 2010-2012, leading the insurer to undertake a reanalysis ofits entire book of business. That analysis resulted in updated ratefilings, updated deviation protocols on scheduled credits anddebits, and refocused underwriting.

The book re-underwrite produced a 35-point improvement in thecompany's accident year loss ratio between 2012 and 2013. Theinsurer wanted to incorporate what it learned from the review intoan underwriting and pricing model that would help avoid mistakes ofthe past and capitalize on future opportunity.

"That's where predictive analytics come in," Hartman says. "Wewanted to start systematizing a underwriting process that has beensolely a judgmental process. We wanted to give underwritersanalyses and information to augment their judgment, relying onbest-in-class tools to differentiate among different risks andopportunities, and better match exposure to the price charged onrisks they wrote."

With 27,000 policies written and 14,000 claims incurred sincethe insurer's inception in 2004, Falls Lake lacked the amount ofinternal data needed to develop its own credible predictive model.The company chose the InsureRight platform from Valen Analytics for riskscoring and underwriting decision support in part because of theplatform's incorporation of a large amount of industry data.

"Valen matched our policy and claims data to the millions ofdata points they have and returned a tool that is customized to fitour business," Hartman says.

Insufficient internal data to develop a credible predictivemodel is a common problem, particularly among small- and mid-sizedcarriers. "Although personal and small commercial carriers tend tohave a good volume of data for traditional business intelligenceneeds, they often need to bring in outside sources for analytics,"Kauderer says.  

Falls Lake began implementing the Valen platform in September2014 and plans to complete the rollout by early 2015. The objectiveis for the tool to supplement, not replace, underwriterjudgment.

"Some companies look for an analytics tool to be a black boxthat provides a yes/no response. We didn't want to do that," saysHartman.

"Our underwriters average between 15-20 years of experience,which is irreplaceable," he adds. "However, they are limited bytime and resource factors. We wanted to provide a framework fordiscretionary pricing and a tool that provides more data, and moreanalyses, than they have ever seen before, then let them applytheir experience."

A question that often arises with the use of third-party datasets and scores is that, because the same scores are available tomultiple carriers, where does the competitive differentiationexist? The answer lies in how insurers layer their own analyticapproach on top of third party data to create a model unique totheir needs.

"Although it's true that some basic data variables are in commonuse by almost all insurance carriers, there is still immensevariation in the number, type, and interpretation of variables usedwhen pricing insurance policies," says Tom Eggenberger, managingdirector of the driver behavior group at AudaExplore.

"Carriers still need to make many complex decisions about how tointerpret each data variable and the relationships between thevariables. Some carriers have more sophisticatedanalytical capabilities, which allow them to identify more subtletrends in the data and to set more accurate prices," Eggenbergersays.

"By itself, the [AudaExplore] score doesn't mean anything," saysFelchner. "Let's say you have a wind score of 30. What is thatworth? You need to take your data and look at how those scoresrespond to your outcomes—that's what we had to figure out."

Figuring that out involved ACUITY's actuaries taking years ofunderwriting and claim data from its data warehouse and running itagainst the PLI and ALI scores to determine how factors related tobusiness outcomes, using Towers Watson's Emblem software as thecompany's predictive modeling platform. Any new factor that ACUITYconsiders for rating undergoes a similar analysis.

Advance of Analytics

Expect insurers to continue to apply what they've learned toanalytics and find ways for it to advance businessoutcomes. "Even with all the progress they've made,insurers have only scratched the surface of what analytics can do,"Dibble says. 

"More and more, the better business will go to companies thatare priced right," says ACUITY's Tures. "Those who use predictiveanalytics to guide pricing precision and decision making will win,and those who don't will fall further and further behind."