P&C insurers have increased their use of predictive modeling in most every line of business. However, they largely do not apply data-driven analytics uniformly throughout the enterprise, and usage fluctuates significantly by line of business and company size, according to Towers Watson’s fifth annual “Predictive Modeling Survey.”

Predictive modeling has helped improve insurers’ bottom lines, Towers Watson said; 85 percent of personal and 96 percent of commercial carriers reported positive impacts on rate accuracy; 80 percent personal and 78 percent commercial reported positive impacts on profitability; and 80 percent of personal and 74 percent of commercial carriers reported positive effects on loss ratios.

The effect on top-line results was less significant: 45 percent personal and 48 percent commercial reported a positive impact on the expansion of their underwriting appetite; and 35 percent of personal and 39 percent of commercial reported a positive impact on market share.

“Personal lines carriers operate in a highly competitive, mature market, so it’s not surprising a high percentage have adopted many aspects of modeling,” said Klayton Southwood, senior consultant, Towers Watson. “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.”

The survey questions the ways insurers are applying predictive models to support underwriting, pricing, claim management and other core functions, Towers Watson said, and found that 80 percent of personal auto and 62 percent of homeowners insurers are using modeling techniques.

Among commercial carriers, 33 percent of general liability and 32 percent of commercial property carriers use predictive modeling; 60 percent of commercial auto and 53 percent of commercial property carriers plan to introduce them into their business. Nearly half, 45 percent of specialty lines carriers said they plan use predictive analytics in the future.

Also see Views from the Front Lines of the Data-Analytics Revolution

“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. “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.”

Large carriers are more likely to use predictive models than small carriers, for homeowners. For example, 74 percent of large carriers, vs. 38 percent of smaller carriers use them. Among small carriers, 61 percent said they use predictive models when necessary, but attempt to differentiate themselves via service and claim-related matters rather than modeling, Towers Watson said.

“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,” Towers Watson said.

Carriers that offer usage-based auto insurance frequently have built upon predictive models, Towers Watson said; 45 percent of participants that write personal lines auto insurance have formal UBI plans, a 10-percentage-point increase from last year; 12 percent of commercial auto carriers either have UBI products or plan to launch them in the next year. Last year, none of the commercial auto carriers had launched commercial auto UBI programs, and 4 percent said they planned to start one.

Register or login for access to this item and much more

All Digital Insurance content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access