Usage Of Predictive Models For Property/Casualty Insurers Grows

NEW YORK, March 20, 2014 — Property & casualty (P&C) insurers have increased their use of predictive modeling in virtually every line of business over the last year, according to a new survey by global professional services company Towers Watson (NYSE, NASDAQ: TW). However, most insurers do not have a comprehensive company-wide approach for using predictive modeling for all core functions.

Towers Watson’s fifth annual Predictive Modeling survey explored the ways insurers are applying predictive models to support their underwriting, pricing, claim management and other core functions. The survey found that in most cases, insurers are not applying their data-driven analytics uniformly throughout the enterprise, while overall usage fluctuates significantly by line of business and company size.

“The survey demonstrates a real willingness by carriers to embrace predictive modeling programs, but in many instances, the actual investment in, or execution to establish these frameworks, has been incomplete or targeted to specific business lines or operational needs,” said Brian Stoll, director, P&C practice, Towers Watson.

Stoll offered several possible reasons why. “It could be due to the financial crisis that insurers put many investments on hold and renewed focus on the expense side of the balance sheet, or maybe a narrow vision of predictive modeling’s applications and potential. Perhaps data, people or cultural challenges are a factor, or some are only applying data-driven analytics when an area is underperforming. Whatever the reasons, a compelling case can be made that well-executed predictive modeling provides better pricing guidance to underwriters.”

Diverse Uses and Approaches

The survey revealed that more personal lines carriers (80% personal auto, 62% homeowners) are currently using modeling techniques than commercial lines carriers (33% general liability, 32% commercial property), which have been slower to adopt modeling but also have plans to introduce them into their business (60% commercial auto, 53% commercial property). Specialty lines carriers expressed an interest in applying predictive modeling to their business with nearly half (45%) saying they plan to do so in the future.

Nearly all carriers said predictive modeling has led to favorable bottom-line results, with positive impacts on rate accuracy (85% personal, 96% commercial), profitability (80% personal, 78% commercial) and loss ratio improvement (80% personal, 74% commercial). Respondents saw less significant benefits to their top-line results, such as modeling’s positive impact on the expansion of their underwriting appetite (45% personal, 48% commercial) and on market share (35% personal, 39% commercial).

“Respondents are really tailoring their programs to focus on specific market realities,” said Klayton Southwood, senior consultant, Towers Watson. “Personal lines carriers operate in a highly competitive, mature market, so it’s not surprising a high percentage have adopted many aspects of modeling. On the other hand, commercial lines carriers face less intense pricing pressure in some segments, in part due to heterogeneous risks and the heightened reliance on individual risk underwriting expertise, particularly in large risk/specialty lines.”

Large carriers are much more likely to use models than small carriers (e.g., with homeowners, 74% versus 38%). The majority of small carriers (61%) noted that while they use predictive models when necessary, they seek to differentiate themselves via service and claim-related matters rather than by modeling. Large carriers are more active in using predictive analytics to improve the financial performance of their claim departments, and see greater benefits to their top and bottom lines, while some smaller carriers have concerns about adverse top-line ramifications related to defending market share and retention of existing business.

Many automobile carriers that have successfully implemented predictive models have built on their modeling initiatives with usage-based insurance (UBI) programs. Forty-five percent of respondents that write personal lines automobile now have formal UBI plans (a 10-percentage-point increase from last year). Twelve percent of commercial automobile carriers have either launched UBI products or plan to do so in the next year, a notable upswing from last year, when none of the respondents had launched commercial auto UBI programs and only 4% of commercial auto carriers had plans to start one.

Data and Communications

The majority of carriers are exploring new internal and external data to improve the sophistication and power of their models, according to the survey. Commercial lines carriers tend to focus more on external risk-specific variables and sociodemographic data, while personal lines carriers stress variable interactions to strengthen their models. Personal lines carriers are also likelier to apply modeling in the form of rating plan adjustments by creating or revising rating/tier variables and relativities, while standard commercial lines carriers balance pricing and risk selection responses to a greater extent, allowing them to keep more of their risk selection and pricing approach proprietary.

Carriers’ communication with their agents about modeling could improve. Less than half provide their agents with relevant insights concerning modeling, and only a fraction involve agents in the model-building process (7%), explain pricing models (17%) and communicate model changes in advance (17%). Carriers using captive agents (50%) believe their agents have more understanding of modeling’s impact on risk appetite, compared to participants using independent agents (30%); respondents using captive agents (50%) also say their agents approve of data-driven analytics more than participants using independent ones (33%). 

About the Survey

Towers Watson’s fifth annual Predictive Modeling Survey included 59 U.S. P&C insurance executives. Respondents were relatively evenly divided between midsize and large P&C insurers as measured by 2012 annual direct written premium, with each representing a 39% share of the total number of respondents. Those carriers with under US$200 million in annual direct written premium represented a smaller portion (22%) of total respondents. Respondents were weighted toward carriers that write primarily commercial lines (54%), compared with carriers that write primarily personal lines (37%).