Advanced Analytics Transforming Insurance with Profound Implications for Competitive Dynamics, ISO’s Chief Says

NEW ORLEANS, October 29, 2007 – The application of advanced analytics is transforming insurers� operations and processes, with profound implications for competitive dynamics in the future. These new advances will enable the best of the best to wring even more actionable information out of available data and to tap previously unusable data. But even today�s leading-edge insurers risk falling behind one day if they don�t master both the art and science of predictive technology and apply it all along the value creation chain, according to an industry leader.

�Escalating competitive pressures cut the number of insurers serving the United States by a third in a decade and a half,� said Frank J. Coyne, chairman, president, and chief executive officer of ISO. �And insurers face a daunting array of other challenges, including the prospect of ever-increasing catastrophe losses. But insurance cycles are nothing new, and success will always require commitment to the core fundamentals underwriting, pricing, loss settlement, and risk management.

�Strong execution against the fundamentals will always require transforming vast amounts of high-quality data into intelligent decisions,� the ISO executive said in remarks to the 800 attendees at ISOTECH, the insurance industry�s premier technology conference. �But advances in technology and analytics are changing the nature of superior execution against the fundamentals raising the bar.

�Moreover, breakthroughs in technology are transforming the competitive landscape in ways that will benefit some insurers at the expense of others,� said Coyne. �To survive and thrive, insurers will need systems capable of analyzing and executing against vast amounts of new and varied information. And they�ll need to connect systems and processes in ways that enable information from each link in the value creation chain to create additional value at other links.

�From product development and marketing to underwriting and rating to claims and reinsurance decisioning the application of advanced analytics to ever-larger and more detailed databases is transforming business processes and improving decisions,� said Coyne. �Huge changes are just over the horizon for lines ranging from personal auto to workers comp. I can�t stress enough that we are at the beginning of a fundamental change in the business of insurance.

�For example, having already developed sophisticated predictive models for personal auto based on hundreds of address-specific variables scientifically shown to affect loss experience, researchers are now working to make next-generation personal auto models even more powerful by adding variables based on the characteristics of individual vehicles such as horsepower with the necessary data obtained by decoding vehicle identification numbers,� said Coyne. �Moreover, researchers are also developing predictive models based on address-specific variables for commercial auto and homeowners. And the use of advanced predictive modeling based on huge amounts of highly granular data is taking hold in workers comp.�

Predictive modeling enables workers comp insurers to identify scientifically the variables affecting losses and to build rating plans that attract good risks, Coyne explained. �Where insurers can�t deviate from bureau rating plans and loss costs, insurers may be able to use the same predictive models to enhance underwriting or marketing decisions.

�Sophisticated predictive modeling is also being used to identify the claims with the greatest potential for becoming ultraexpensive and to target them for intensive case management by healthcare professionals,� said Coyne. �Predictive models of this sort are already widely used in the health insurance sector. Now, some insurers are starting to use them to manage workers compensation claims and cut costs. Other new and promising ground in workers comp includes the use of advanced analytics to stem premium leakage.�

Noting that the value creation chains for all lines of insurance have a lot in common, Coyne cited claim fraud, in particular, as a problem for all lines. �Using the rule of thumb that fraud adds ten percent to property/casualty loss and loss adjustment expenses, claim fraud cost insurers approximately $28 billion last year alone, even without including the billions lost to claim fraud in the health insurance sector,� he said. �Today, leading-edge insurers are using predictive analytics, such as scoring, and data-visualization tools, such as link analysis, to take a bite out of fraud, settle meritorious claims more quickly, and increase customer satisfaction.�

Those insurers can pass cost reductions on to their customers, obtaining an immediate boost in the fight for profitable business. But those same insurers can also invest savings in the development of additional analytics, giving them an even bigger edge on their competition.
�And more advances are on the way. New technologies, such as text mining, are poised to unlock the almost limitless and highly informative but unstructured data in claim adjusters� notes information previously beyond the reach of those using scoring to detect potential fraud,� said Coyne. �And new access to that same unstructured data will trigger further refinements to the advanced predictive models already beginning to transform marketing, underwriting, and pricing.�

Turning to catastrophes, Coyne acknowledged the effort �to restore New Orleans to its former glory,� but cited the �still visible signs of the almost unimaginable devastation caused by Hurricane Katrina.�

�Despite dire predictions, I�m happy to say that no hurricanes struck the U.S. in 2006, and we�ve only been hit by one so far this year,� said Coyne. �But we can�t allow some good luck to lull us into a false sense of security someday, somewhere, we�ll face a catastrophe far more devastating than Katrina.�

Coyne noted that 2005�s $62.3 billion in catastrophe losses dwarf even those in 2001, when terrorists destroyed the World Trade Center, and those in 1992, when Hurricanes Andrew and Iniki struck. �Superficial analyses indicate several of the worst hurricane catastrophes on record have occurred in the past few years,� he said. �But a more sophisticated analysis, using AIR Worldwide catastrophe models to impose past storms on today�s exposure base, reveals that only one of the ten most costly hurricanes took place during the last decade. The inescapable conclusion is that the effects of exposure growth have far outweighed any effects of global warming and cycles in sea surface temperatures.�

Coyne also highlighted several factors driving exposure growth, including an increasing number of residential properties. �The number of single-family homes, apartments, and condos grew 15 percent countrywide in the last ten years, with growth in some hurricane-prone states far exceeding the national average,� said Coyne. �Other census data shows that 63 of the 100 fastest-growing counties are in hurricane-exposed coastal states, with 50 of them being in five hurricane-prone states. In fact, 12 of the fastest growing counties including the very fastest are in Florida, the state hit by more hurricanes than any other.�

But it isn�t just the numbers of homes and people that are increasing. The average size of new single-family homes has risen almost every year since 1982, climbing from about 1,700 square feet to almost 2,500 square feet. �Moreover, new homes have gotten more elaborate, and those with older homes invest billions every year upgrading them,� said Coyne. �All of this contributes to exposure growth. And so does inflation in replacement costs. Bottom line, exposure growth will continue to drive catastrophe losses upward.�

Coyne cited analyses by AIR Worldwide that indicate catastrophe losses will double about every ten years just because of exposure growth. �Events causing $100 billion or more in insured losses are already easy to imagine,� he said. �If a Category Four hurricane made landfall in New Jersey and swept its way through the metro New York area and points north, insured losses could total about $150 billion. A magnitude 8.3 earthquake with an epicenter near San Francisco could cause insured losses totaling about $180 billion.

�Potential losses from natural catastrophes, combined with those from terrorism and other emerging risks, such as genetically modified organisms, nanotechnology, and pandemics, contribute to the need for sound enterprise risk management,� Coyne added. �So too do myriad operational risks, such as the potential for a catastrophic fire or computer meltdown at an insurers� home office.

�Bottom line, art and science are coming together in new ways all along the insurance value creation chain. We are at the beginning of an intellectual and technological arms race that will remake the insurance business,� said Coyne. �Those insurers that succeed in developing and deploying advanced analytics all along the value creation chain can look forward to a long and prosperous future if they continue to invest in new and better analytics and new and better data. Other insurers face a far different future, with even the best of the best today being at risk of falling behind as new technologies come on line.�

About ISO

ISO is a leading provider of products and services that help measure, manage, and reduce risk. ISO provides data, analytics, and decision-support solutions to professionals in many fields, including insurance, finance, real estate, health services, government, and human resources. Professionals use ISO�s databases and services to classify and evaluate a variety of risks and detect potential fraud. In the United States and around the world, ISO�s services help customers protect people, property, and financial assets. For more information, please visit