It's generally accepted that the first automobile policy in theU.S. was sold in 1897 in Dayton, Ohio. For more than 100 years,automobile insurance would be underwritten fundamentally the sameway as that first policy: manually and customer-by-customer.However, the effort that began more than 10 years ago to applybusiness intelligence to auto-insurance underwriting hastransformed what had once been an art into a standardized andautomated process at many carriers, where manual processing is theexception rather than the rule.

“Personal auto is clearly the most advanced and most mature inits use of business intelligence and analytics. It really is ascience,” says Deb Smallwood, founder, Strategy Meets Action (SMA).She believes that homeowners is the next line poised for a processevolution, with the only limiting factor being gaps in availabledata.

The adoption of advanced analytics in commercial lines has beenslower. “There's a continuum [in automation] from how much marginthere is in the business and how complex it is,” says MatthewJosefowicz, managing director at Novarica.

“Low-value business owners or workers' compensation lines aregoing to start to look like personal lines, with a greater emphasison straight-through processing. Complex liability will take longerto automate, and there's a question of the marginal value ofautomating it at all. But certainly there is value in usingbusiness intelligence to make those underwriters more efficient andgiving them better tools to do their job,” he explains.

Commercial Success

That's not to say that carriers have not experienced success inleveraging intelligence in the commercial lines underwritingprocess. Chesapeake Employers' Insurance Company, Maryland'slargest writer of workers' compensation insurance, has been using apredictive analytics solution from Deloitte since 2008 to scorerisks and suggest the proper tier and pricing for an individualaccount. Now, the company is targeting other enhancements to theunderwriting process.

“The high-level objectives are to make underwriting and theprocess of analyzing risk more efficient, to make underwriting moreaccurate, to increase the speed of processing and to create abetter experience for our agents [when] working with underwriters,”says Steve Orr, Chesapeake's senior vice president of Marketing andTechnology.

Chesapeake is in the midst of a multi-year project to replace a20-year-old, in-house-designed policy administration system. Thefirst stage of that replacement, completed earlier this year,involved incorporating an Oracle Service Bus into the company's ITarchitecture in order to create SOA capabilities that would allownew components to be added.

The first component will be the FirstBest UMS underwritingworkstation. With final development completed in early November,the company is currently in the testing phase and plans a March2014 rollout. A key capability of the FirstBest system will beintegration with external data sources.

“The workflow in UMS will be utilized to automatically assemblea lot of the third-party information that underwriters have to goout and get today,” Orr says.

Examples include Dun & Bradstreet data, vehicle informationand corporation-licensing information from the state. When anapplication comes to the underwriter, the system will present atask manager showing the information that has been gathered and theitems that need review. The FirstBest system will also integratewith Chesapeake's risk-scoring platform to provide straight-throughprocessing for the majority of accounts that generate less than$10,000 in annual premium.

“We're confident that the workflow FirstBest provides will giveus the confidence to do straight-through processing that we haven'thad with our current platform,” Orr says. “The advantage to theagent will be faster—even immediate—turnaround, as well as theability to run 'what-if' scenarios while they are on the line withthe customer. Also, underwriters who today need to spend their timeon the smaller applications will be able to apply their effort tomore complex accounts, which will help us expand our marketingefforts.”

Global-commercial insurance and reinsurance firm XL Group is inthe process of creating its “Global Underwriting Platform.”Traditionally, underwriting processes at XL have been paper-basedor handled by different systems based on lines of business. Littleinformation was able to be shared across different underwritingteams, and risk data was often confined to underwriting files,limiting its ability to be analyzed.

The new platform is designed to allow underwriters tocollaborate with each other, access external data and integratewith internal administration systems. Kurt Schulenburg, theinsurer's vice president of IT Strategy, says that the ultimateobjective is to transform the underwriting process.

“First, we wanted to make underwriting a much more efficientprocess through technological automation and improved underwritingworkflows. Underwriters will be able to spend less time oncompleting tasks and more time on risk analysis and evaluation,”Schulenburg says. “Second, we want to improve analytics throughoutthe process. Working in our current environment with disparatesystems and many manual handoffs, it's difficult to performanalytics or even to present all the information in one spot to anunderwriter.”

XL's global platform includes several newcomponents—FirstBest's UMS to provide a common workbench forunderwriters, Accenture Duck Creek to create a singleadministration system for the company's North American ISO lines ofbusiness, and SAS Visual Analytics.

“That [platform] will give us one interface for all P&Cunderwriting—a common look and feel, a common way of capturinginformation and a common way to get from an application submissionto policy issuance to endorsements and renewals,” Schulenburgsays.

One of the most significant impacts of consolidating policy andunderwriting data across classes of business will be improvedvisualization. “We will now have location management capabilities,”Schulenburg says. “By capturing and consolidating location dataevery time we underwrite a location, there will be a visualizationthat not only shows how close that risk is to earthquake and otherhazard zones, but also to where XL already has exposure in thatgeography.”

The initial release of the system to support general liabilitywas completed in 2012. By the end of 2014, XL plans to have abouthalf of its P&C premium on the platform; by the end of 2015,that amount should exceed 90 percent.

Schulenburg says, “Our goal is a 40 percentpremium-per-underwriter gain for those groups that have deployedthe platform. Our current release for general liability showsthat's very achievable. Property and workers' compensation arecoming next, and we plan to hit that [percentage gain] there aswell.”

More Than Automation

Turning underwriting from an art to a science isn't just aboutautomation; it's about making more precise underwritingdecisions.

“Once we generate greater efficiencies for everybody, the nextquestion is how we can gain the benefits of all the new data we arecapturing,” explains Schulenburg.

There has been an explosion in underwriting data. There aresources for geocoding, geographic information, aggregated consumerinformation, commercial data, tax information and more, as well aseasier ways to collect that information electronically. But thisdata proliferation creates its own challenges.

“A human brain can only look at a few data points and correlatethem,” Smallwood says. “The computer can do hundreds or thousandswithin predictive models. However, we're just in the early stagesof applying analytics to commercial markets.”

XL Group's Strategic Analytics team is building predictivemodels based on SAS Visual Analytics. The intent is for thoseanalyses to connect the dots within and across risks, helpingunderwriters make better informed decisions. But it's no easytask.

“The ability to implement a predictive model is based on volumeand consistency of risk, which is difficult to do in highly complexcommercial lines,” Schulenburg says. “Within professional lines,we've identified some cases where there was enough volume andconsistency to implement a predictive model, but we're stillresearching how to make that work for property and casualty.”

Change Management

In addition to modeling challenges, companies can also faceinternal resistance to underwriting transformation.

“There is a significant cultural issue,” Smallwood says.“Insurers need to be willing to embrace business intelligence totransform the art of underwriting into a blend of science and art.It has to start with the mandate from executive leadership, througheach line-of-business head to the underwriting department. It isnot about eliminating the underwriting, but augmenting theunderwriting-risk analysis, decision and pricing with expandedinsights and intelligence about the risks.”

Orr says, “Everyone is excited about greater integration, nothaving to re-key data and increased technological automation basedon the objective parts of underwriting. That's the easy part. Butit's harder to target the judgment parts of the process. Changingthe way you make decisions, the ways you price; the risks you workon—that's the next challenge.”

Showing underwriters the benefits and results of businessintelligence and anlaytics is the key to overcomingchange-management challenges. “As analytics is being introduced, itshould be rolled out as a tool,” Smallwood explains. “Don't forceit on the underwriter, and allow the underwriter to override [therecommended action] with explanation. Then, run reports showing thedifference in loss ratio between the accounts where underwritersoverrode the system and where they did not.

“Overall the insights and intelligence are correct more oftenthan not,” she adds. “Over time, the underwriters will begin toembrace analytics as a tool to augment their art.”