A View Inside the "Black Box:" A Review and Analysis of Personal Lines Insurance Credit Scoring Models, A View Inside the "Black Box:" A Review and Analysis of Personal Lines Insurance Credit Scoring Models Filed in the State of Virginia

In order to reveal and better understand the inner workings of insurance credit scoring models used by the vast majority of personal lines insurers, the authors obtained nine private passenger automobile and two homeowners’ filings from nine insurance groups from the Virginia Bureau of Insurance. Within these filings the authors found three categories of models created by either Fair Isaac & Company, ChoicePoint, or the insurance companies providing the filings. Based on the review and aggregation of these filings, the authors will describe the data sources, scoring functions, scoring algorithms, model variables, and statistical details of these models. In addition to descriptive information, interpretive and explanatory details for the models will be included based on the authors’ past experience in conducting predictive modeling projects that included both mainstream and non-traditional predictive variables as well as personal credit information. As a result, the readers will gain a better understanding of how the insurance industry utilizes credit information to formulate insurance credit scores.