Insurance executives are still grappling with an all-too-slowlyrecovering economy, declining returns on equity and increasingpressure to turn a profit any way they can—and carriers offeringHomeowners' coverage face added volatility in light of recentcatastrophic weather events like Superstorm Sandy.

In order to bring some balance to this equation, there is agrowing need to better understand and manage risk in Homeowners'insurance.

The numbers tell the story: According to A.M. Best and theInsurance Information Institute, Homeowners' combined ratio swungfrom a high of 158.4 percent in 1992 to a low of 88.9 percent in2006. The average combined ratio for Homeowners' carriers from2008-2011 is 113 percent, compared to 102 percent across all otherP&C lines.

As carriers look to address this conundrum, the notion of optingout of Homeowners' isn't a viable one for many—and would meanforegoing multiline advantages, such as:

• Meeting state regulatory requirements for carriers to writeHomeowners' in order to write Auto.
• Responding to the significant portion of consumers that preferto bundle their Homeowners' and Auto insurance policies.
• Spreading market and regulatory risk of an individual line overa broader portfolio of risks.
• Leveraging systems and operating processes to support multiplelines as a scalability benefit.

While carriers continue to mitigate weather losses bygeographically dispersing and diversifying their Homeowners' riskexposures, historical results beg the question of whether thecurrent risk-management practices they have in place aresufficiently effective—and whether carriers even possess a clearunderstanding of the risks they are writing.

“There is more emphasis on risk management as catastrophes aregetting bigger and worse,” says Morgan Davis, independent directorof Montpelier Re Holdings Ltd. “I've heard from many CEOs who worryabout their company's ability to survive tough years like what weexperienced in 2011. CEOs are asking themselves, 'Do we know howmuch risk we have?'”

According to Ernst & Young's Global Insurance Outlook, the No. 1 thingcarriers can do to improve their combined ratio is to achievesuperior underwriting. Yet carriers face challenges in underwritingas they struggle to understand the risk profile of the propertiesthey write and renew from year to year.

The magnitude and volatility of historical combined ratiossupport the notion that unacceptable Property and Liability risksare being systematically accepted and retained through theunderwriting process. Additionally, properties are being renewed atinsurance-to-value levels well short of 100 percent, causingpremium leakage and negatively impacting combined ratios.

This confluence of market realities leaves carriers in search ofdifferent methods to improve the performance of their Homeowners'portfolio. Some carriers are implementing rate increases andgeographic retraction, and many are also turning to the use ofpredictive analytics as a promising technology to help improveunderwriting, claims and marketing.

|

What Is Predictive Analytics?

Predictive analytics uses statistical and analytical techniquesto develop models that enable accurate predictions about futureevent outcomes. Predictive models can take various forms, with mostmodels generating a score that indicates the likelihood a givenfuture scenario will occur. Mining data in order to identifytrends, patterns or relationships is a key component of buildingpredictive models. Predictive analytics enables powerful andsometimes counterintuitive relationships among data variables toemerge that otherwise may not be readily apparent, thus improving acarrier's ability to predict the future outcome of a policy.

How Predictive Analytics Impacts Homeowners'

The use of predictive analytics in Homeowners' insurance hassteadily increased over the past several years. A majority ofHomeowners' insurers have utilized predictive analytics for manyyears in rate-making (i.e. loss-cost relativities, by-perilrating), rating-plan assignment (sometimes called “underwritingscorecards” for tier or company placement, declines andnonrenewals) and price-discount qualification. A widely knownpractice is the use of credit-based insurance scores in manystates.

Homeowners' carriers are also integrating predictive models tohelp with claims handling, marketing and new methods ofunderwriting. Claims analytics models are being used byforward-thinking carriers in several ways, including to:

• Predict overall claim severity
• Focus on early identification of fraud
• Target the likelihood that a claimant will litigate aparticular claim

Marketing departments are taking the lead from financial-serviceorganizations to analyze consumer purchasing patterns and otherbehavioral attributes through the use of predictive models. Thisadditional insight allows marketers to improve both their hit ratio(the percentage of prospective customers who buy a policy) andretention ratio.

Leading carriers have recently discovered better, morecost-effective ways of underwriting risks beyond the use ofunderwriting scorecards. The fundamental problem many carriers faceis the lack of reliable data on the homes they insure, whichdiminishes an underwriter's ability to estimate the expected futureloss performance of a policy. Using predictive models, carriers areable to redesign costly information-gathering efforts, such asproperty inspections, and re-focus underwriting efforts on homesthat are most likely to have insurance-to-value deficiencies orcondition and liability hazards. This allows a carrier to chargethe amount of premium commensurate with the risk on thepolicy.

|

Best Practices in Predictive Modeling

Predictive analytics has many benefits to offer the insuranceindustry, and there are important factors that will enable acarrier to be successful deploying predictive models:

• Good, clean data is key to deliveringresults: Carriers collect considerable amounts of data.When this data is properly structured, carriers can build accuratepredictive models. In the past, larger carriers were better able totake advantage of predictive models because of their large datasetsand ample modeling and IT resources. However, there are now severalthird-party data and modeling resources available to all carriersthat allow the small and midsize companies to compete effectively.Experts who have been using predictive models for decades testifyto the importance of accessing representative and sufficientlysized data samples. Mark Gorman, CEO of The Gorman Group agrees,“Data, especially external data, has become even more important.Carriers have to access third-party data in order to becompetitive.”

• Predictive analytics enables consistentdecision-making: Top carriers utilize predictive models tomake data-driven decisions consistently across their underwritingstaff. These models allow carriers to use evidenced-baseddecision-making rather than relying solely on heuristics or humanjudgment to assess risk. Underwriters thrive when they havereliable information to aid their expertise, and accuratepredictive models have proven to outperform traditionaldecision-making techniques.

• Predicting future performance increasesprofits: Incorporating predictive analytics allows acarrier to anticipate the future performance of a policy, which isvital to managing risk and removing the uncertainty for what theyinsure. Gorman emphasizes the fundamental changes that occur whenadopting predictive analytics: “This represents a completeevolution of the industry in terms of people, process andtechnology. At the same time, what we know from a revenuestandpoint is that carriers who adopt predictive analytics earliergain market share—profitable market share. Carriers who aren'tmoving in that direction are dealing with adverseselection.”

• Using predictive analytics helps carriers know whatthey insure: Using predictive analytics enablesunderwriting, claims and marketing to make evidenced-baseddecisions that lead to better risk selection, pricing and claimshandling. With recent data and technology advancements, carriers ofall sizes can compete on a more level playing field. Predictiveanalytics offers a better, faster and cheaper method to allowunderwriters to assert more control over their portfolio'sperformance. It is possible to counteract the unpredictableHomeowners' market, gain a competitive advantage in underwritingand improve operating performance. While it is impossible tocontrol the weather, it is possible to understand more about thehomes carriers insure and price them accordingly using predictiveanalytics.