P&C insurers say predictive modeling is improving bottom-line results: Towers Watson survey

North American property and casualty insurance companies currently using predictive modeling are seeing positive improvements in bottom-line results, according to a Web-based survey by Towers Watson.
Predictive modeling uses advanced statistical modeling techniques, along with critical company and external data related to individual policyholders, competitors, marketplace conditions and customer behavior, to help underwrite risk. One example might be credit scoring.
One hundred and nine executives from U.S. and Canadian property and casualty carriers participated in Towers Watson’s second Web-based survey. Both annual surveys focused on how predictive modeling is being used to support rating/pricing and underwriting/risk selection plans at their companies.
The second annual survey was conducted in late 2010. Most participants (U.S. and Canada) focused on accounts of less than US$100,000 in premiums.
Ninety-seven U.S. executives and 12 Canadian executives participated in the second annual survey. Of the 43 U.S. companies that responded to both surveys, 88% said the use of predictive modeling enhanced rate accuracy (up from 77% when the survey was first conducted in 2009).
Seventy-six per cent of respondents said they realized an improvement in loss ratio (versus 57%), and 68% said that it improved profitability (versus 55% a year ago).
Additionally, 42% said the use of predictive modeling has furthered the expansion of their company’s underwriting appetite (up from 40% in 2009). Thirty-nine per cent indicated it helped increase market share (versus 33%).
The current use of predictive modeling in the United States is up by roughly 10% across all lines of business except commercial property/business owners package (BOP), which remained relatively flat, the survey found.
Also, personal lines carriers have been much more active in core predictive modeling activities over the past two years.