01:10 PM
Connect Directly

Predictive Modeling Emerges as Competitive Differentiator in P&C

New research from Towers Watson and a case study from Liberty Mutual show how analytics are becoming more entrenched across the P&C enterprise, especially for commercial lines.

Predictive modeling is fast becoming table stakes in the P&C industry, according to recent research from Towers Watson.

Eighty-five percent of the 69 insurers polled by Towers Watson "use or are planning to use" predictive modeling. Commercial lines carriers, who traditionally lagged their personal lines counterparts in embracing the technology, are planning or implementing programs at a 70% clip.

Survey findings indicate that underwriting, risk selection, rating and/or pricing are driving predictive modeling investment. However, Towers Watson director Brian Stoll notes that the profitability of the channel "encourages P&C insurers to find even more ways to extend predictive modeling applications and further access the benefits it can offer."

An example of this can be found in a Liberty Mutual webinar, in which the insurer's workers' compensation division discusses its success using predictive modeling in the claims process.

"Almost 50 percent of most workers compensation policyholders' claims drive 90 percent of total claim costs," George Neale, EVP and GM for claims in Liberty Mutual Insurance's Commercial Markets strategic business unit, says in a statement. "Identifying these early and getting them the proper resources quickly, delivers the best possible outcomes for injured workers and their employers."

The company incorporated a predictive model into its VantageComp claims management process in 2004 that has helped it identify those outliers quickly and easily.

"We evaluated more than 825,000 lost time claims and 140 million individual medical billing transactions," says Paul Ivanovskis, the Liberty Mutual senior managing actuary who developed the model, in a statement. "To validate the accuracy of the updated model, we ran an additional 200,000 lost time claims – which were not included in the evaluation phase – through it. The model accurately predicted the outlier claims that developed in that 'holdback' data."

"Every one" of the company's claims professionals is trained in the use of the model, adds Maureen McCarthy, SVP, workers compensation and managed care, Commercial Markets, Liberty Mutual Insurance, in the

Nathan Golia is senior editor of Insurance & Technology. He joined the publication in 2010 as associate editor and covers all aspects of the nexus between insurance and information technology, including mobility, distribution, core systems, customer interaction, and risk ... View Full Bio

Comment  | 
Print  | 
More Insights
Newest First  |  Oldest First  |  Threaded View
Register for Insurance & Technology Newsletters
White Papers
Current Issue
Insurance & Technology Digital Issue
Innovation? Check. Core modernization? Check. Security? Check. Today's insurance IT challenges don't stump this year's Elite 8.