In the area of homeowners insurance, U.S. carriers spend about$190 million dollars a year on inspection programs to support riskmanagement of new and renewal business.  Yet manyunderwriters have difficulty quantifying the ROI of theseprograms.  Those who can quantify inspection programresults often find a negative or break-even ROI at best—althoughthese programs are seen as a necessity of goodunderwriting. 

As those who play the lottery say, "You can't win if you don'tplay." This perspective is akin to property underwriters who findthat one property oozing with disrepair, prior damage, oregregiously misrepresented in the underwriting process is likewinning the risk management lottery.

There's no denying the value of a high quality inspection on a questionable risk, but how canunderwriters stack the deck and select more of those propertiesthat need inspection?  And how can a carrier determine ifthe condition hazards they look for are actually drivers of ameaningful amount of loss?  In other words, we sometimesspend so much time and money looking for the needle in the haystackthat we don't pause to ask if we've even found the rightneedle.

Today, most Property & Casualty writers either incorporatesome form of analytics in their business planning and workflow, orare in the process of developing this analytical capability.

The promise of deep insight at all phases of the insuring processthrough the microscope of eventuality not only offers the abilityto create a strong competitive advantage, but also ensurescompanies perform their business to the mission statement theyarticulate.

The very best analytics engagements are, in fact, predictive.These not only guarantee that insurers are on track for what theyaspire to be in the markets they serve, but also mitigate futureexposures through forward-looking analysis of such things as bestof breed business, elimination of risk before losses occur,optimization of business operations, and pricing reflective of theactual exposure insured. 

Beyond applying these powerful techniques to pricing, carriersare now discovering new classes of problems like inspectionoptimization that can be solved to drive improved risk selectionand financial performance.  Traditionally viewed as a costcenter, the inspection program presents the opportunity inforward-looking carriers to become a profit center and keystrategic competitive advantage.   

Inspection Programs

A majority of property writers today supplement theirunderwriting and risk assessment process through the use of on-sitefield inspections. Field inspections create a visual of each risk,an assessment of the quality of the risk against certain exposurevariables carriers assess and develop a snapshot of hazard or otherconditional variables that increase loss potential. A more detailedassessment will also establish updated insurable values, interiorconditions/exposures and violations of such things as code and lifesafety concerns that help score risk desirability, loss potentialand premium adequacy.

Carriers that write homeowners insurance spend a significantpercentage of their operating budget in underwriting for homeinspection work. Many large carriers allocate one to three percentof annual underwriting expense budget to field inspections. Thispercentage is usually higher for mid-smaller companies. Themajority of insurers outsource this work, so cost management andthe efficacy of the program is a high priority.

Working with top property writers, we have discovered that thedecision to inspect, as well as the intent of each risk review, isassociated with long-standing guidelines or traditions, notnecessarily defined on a risk-specific basis. In other words,carriers have "always done it this way", so when certaincharacteristics of risk (like age, size or geographical location)are identified, they have an inspection done. 

However, this paradigm is changing quickly.

After reviewing nearly two million actual field inspectionprojects for property writers, MSB identified that traditionallyonly about 25 percent of inspections performed using today'sguidelines are actionable—or produce information that the carrieracts upon to mitigate or properly price a risk. 

In addition, actionable criteria used by carriers aren't alwaysdirectly tied to loss frequency or severity.  Since therisk management process has never been closely aligned with whatmakes inspections actionable before the order is made, the industryspends over $140 million per year for work that will add noimmediate value to loss experience or the bottom line.

The question at hand would therefore be: Could property writersimprove bottom line results if truly actionable risks were isolatedin advance of the inspection request, allowing these efforts totarget risk identification and mitigation with precision? This isexactly the optimized state that progressive carriers are beginningachieve through the use of proper data and advanced predictivemethodology.

In a recent industry survey conducted by Marshall &Swift/Boeckh, 87 percent of the respondents (U.S. and CanadianP&C carriers) have acknowledged homeowner inspection spendingas a key business problem that needs to be optimized. Some forward-looking carriers have recognized this business problemand desire to construct predictive solutions to recommend idealrisks for inspection that are, in fact, tied to predictors of highfrequency and/or severity of loss.  These carriers areeliminating wasteful inspection costs and disruption to lower-riskcustomers.

New Answers

A property writer's homeowners inspection program can beconsidered to be running in an optimized state when:

• A predictive model is aligned to the front end of theinspection ordering and budget process.
• The model is giving lift to the action ratio of inspections orwith an actionable rate of 60 percent or higher on the year'sexperience.
• Policies are identified for inspections based on the type ofinspection needed.
• The best inspection program for each risk is assigned, which inmany cases is not an actual field visit but might actually be anentirely different or alternative to traditional mediums, such asphone surveys, mailers or mobile surveys.
• And most importantly, companies see bottom line improvementsthrough reduced loss experience and a closer alignment of premiumwith exposures insured.

Optimizing the InspectionProgram

Data Strategy: Bringing together all of theexisting historical inspections data is a good start, but carefulconsideration should be paid to assemble a comprehensive dataset soall the relevant predictors that will help the model perform wellduring actual production conditions are identified. Modeling inthis problem space is a challenge of data quantity and quality.

It is common for carriers to start developing inspectionoptimization models with data that is available internally withinthe organization. This approach of using limited internal datapresents serious challenges in developing a robust predictivemodel. A carrier's trusted business partners as well asnon-traditional sources of data can be critical to the rightinformation acquisition solution in this problem space. An external data acquisition strategy is critical and enough timeshould be spent in qualifying valuable industry benchmarks,econometric trends, financial data, and location specificinformation.

About 30 percent of carriers that responded to a nationalindustry survey conducted by MSB, identified the availability ofgood data as the significant challenge in initiating a project tosolve the homeowner inspection optimization problem. Thesechallenges included:

Predictive Model Development: The models shouldbe validated enough to ensure they do not over-fit or suffer fromthe problem of performing well on the training dataset, but failingon actual production settings. Due to the limited amount ofhistorical inspections data, modeling teams will also encounterproblems in handling Selection Bias. It is recommended thatcarriers utilize an experienced modeling team that has successfullyapproached this problem space or ones technically similar innature.

Implementing the Solution: As carriers areworking towards optimizing the homeowner's inspection program, itis critical that alternate inspection techniques are thoroughlyevaluated. One has to look beyond the traditional exteriordrive-by, and exterior/interior inspections.  The newprogram should seek to optimize the balance between inspectionexpenses and underwriting accuracy.   In fact,different types of inspections are naturally geared to differentkinds of risks and the application of any model predictions shouldapply this concept.  Good deployment planning, workflowintegration design, and continuous model performance validationbased on inspection results from the field and underwriter actionis critical for the program's success.

Get Started Now

Getting started is imperative and the rewards are substantial.First, a carrier can benchmark the actionable rate of the currenthomeowner's inspection program and gain a sense of the financialimpact of enhancing the efficacy of the inspectionprogram.  Time should be spent in identifying actualdrivers of loss by peril, frequency and severity.  Manycarriers have this information from their efforts in by-perilrating and the same insights can be applied as a starting point toevaluate whether today's inspection program looks for the rightcriteria.

With more insight into the actual performance of the currentinspection program and fundamental drivers of loss, carriers canbegin the process of optimization. Here are some areas to focuson:

• Create a good external data acquisition strategy. Securing theright dataset is directly proportional to the predictive power ofyour inspection model. 
• Treat the inspection optimization project as a business problemand not purely as a modeling challenge. 
• Evaluate alternate inspection methods in addition to thetraditional field inspections.

Since the experience in optimizing business operations with dataand predictive solutions is becoming more standardized, manycarriers are embarking on information based strategies to bettercompete in today's evolving market.  Applying acomprehensive data and analytic strategy throughout the solutiondelivery roadmap, carriers should be able to achieve an inspectionactionable rate of 60 percent or higher and an overall inspectionprogram ROI of 5:1.

(Chris Cartwright is CEO of Marshall & Swift/Boeckh, asupplier of local building cost information as well as residentialand commercial property valuation technology and services in theUnited States and Canada.  Services also includeMSB's InFocus Analytics, business intelligence, and industryleading "outsourcing" solutions.)