Over the last decade, insurance companies have become immersed in applications of predictive modeling. One application of predictive modeling that has received a lot of attention but has not been implemented widely as of yet is an analysis of customer conversion, or the likelihood of writing a customer once they contact you and receive a quote. There are a number of challenges to this type of analysis, including availability of data, breadth of data, and the difficulty in measuring elements that are key to the analysis.
To begin to address these difficulties, comscore, Inc. and Pinnacle Actuarial Resources, Inc. have embarked on groundbreaking research to develop insurance demand models, predicting the likelihood of converting insurance customers that receive quotes on the internet. This session will discuss findings from this research and will discuss other planned areas of analysis.
Topics to be discussed will include:
- Examples of factors that drive differences auto insurance demand
- Discussion of how price differences impact customer purchasing behavior
- Application of text mining to the analysis of conversion
- Comparison of characteristics of those that are shopping on the internet to those of the general population
- How the customer demand changes as they progress through the purchase process

Moderator:
Roosevelt Mosley, Pinnacle Actuarial Resources, Inc.

Panelists:
Nick Kucera, Senior Statistical Analyst, Pinnacle Actuarial Resources, Inc.
Kevin Levitt, Vice President, comScore, Inc.