“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,” Stoll said.

The fifth annual Predictive Modeling survey explored the ways insurers are applying predictive models in the industry, including responses from 59 U.S. P&C insurance executives. Click through the following slides for the survey's key findings.

A Solid Base for Implementation

P&C insurers increasingly have the basic tools and capabilities they need to pursue data-driven analytics integration throughout the organization, suggesting consistent enthusiasm for predictive modeling.

The survey reveals that more than 75% of personal lines and small to mid-market commercial lines respondents view predictive modeling as very important to their business. All personal lines respondents indicated that predictive modeling has at least some degree of importance for sophisticated underwriting and risk selection techniques for rating and pricing, and 83% of personal lines respondents cited predictive modeling as “essential.”

Similarly, 79% of commercial lines respondents agreed that predictive modeling functions were “essential” or “very important,” as did 56% of large account and specialty lines carriers.

Specialty lines carriers also expressed interest in predictive modeling applications, with 45% indicating they have future plans for implementation.

The value of predictive modeling is reflected by increased implementation. For all lines of business, the use of predictive modeling has increased. In particular, usage in personal automobile grew five percentage points from 2012, bringing total implantation to 80% among respondents, while homeowners increased to 62%. Among the largest gains over 2012 were workers' compensation (9 percentage points) and general liability, commercial multiple peril and business owners' policy (7 percentage points).

Favorable Bottom Lines

The survey reports that nearly all carriers experienced favorable bottom-line results because of predictive modeling, creating positive impacts on rate accuracy, profitability and loss ratio improvement.

Results showed that benefits were less significant, however, to respondents' top-line results, such as modeling's impact on the expansion of their underwriting appetite and on market share.

“Respondents are really tailoring their programs to focus on specific market realities,” said Towers Watson senior consultant Klayton Southwood. “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.”

In terms of renewal retention, there was a greater disparity between personal and commercial lines carriers. 25% of personal lines carriers reported a positive impact, while 52% of commercial lines respondents reported a positive impact.

The survey suggests that the disparity can be attributed to the lack of product differentiation and keen price competition in personal lines, as well as customers' willingness to switch carriers. Commercial lines carriers' positive retention may be due to the potential for predictive modeling for improvement of underwriting and rating accuracy, allowing carriers to attract customers with more targeted premium rates. Commercial policyholders, in general, have broader insurance relationships with carriers, and heavier dependence on customized/differentiated services, reducing price sensitivity and willingness to switch carriers.

Data and Communications

Survey findings reveal that a commitment to predictive modeling is more than just building and applying technical models. Improved communications concerning the measurable value that strategic application that predictive modeling offers to all key stakeholders is imperative for effective implementation and integration.

While insurers say they are fostering greater agent understanding and approval of predictive modeling, the survey findings reveal a communication gap between carriers and agents.

Less than half of survey respondents provide relevant insight to agents related to modeling efforts, and only a small fraction of respondents involve their agents in the model-building process, explain their pricing models to agents or communicate model changes to agents in advance.

However, the majority of carriers are using internal and external data to improve the sophistication and power of their models. Commercial lines carriers, in particular, tend to focus on more external risk-specific variables and socio-demographic data. Personal lines carriers, on the other hand, stress variable interactions to strengthen their models and are more likely to apply modeling in the form of rating plan adjustments by creating or revising rating/tier variables and relativities.

Survey results from the past two years show the increased willingness to embrace predictive modeling programs, but actual investment or execution is often tentative, or falls short. Towers Watson suggests that a more comprehensive, strategized and aggressive approach to predictive modeling implementation is necessary for effective implementation.