P&C insurers have increased their use of predictive modeling in almost every line of business. However, most 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 says; the effect on top-line results has been less significant.
"Personal lines carriers operate in a highly competitive, mature market, so it's not surprising a high percentage have adopted many aspects of modeling," says 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 says, 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 it into their business. Nearly half (45 percent) of specialty lines carriers say they plan to use predictive analytics. "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 says.
