Abstract: A system and method are described to improve computer performance of statistical predictive models through the creation of automated insights. The method involves apportioning some of the modeling data to create an Insights Dictionary. Each entry in the Insights Dictionary is a label-value pair that is present in the apportioned data. For each entry, statistical descriptors of the Target, for example it's average, are computed among all members of the apportioned set where the label-value pair is present. Entries that are not statistically significant are aggregated with related peer entries until they are statistically significant or cannot be further aggregated. The Insights Dictionary is then used as a lookup table to transform raw predictors in the remaining modeling data set into insights, automatically generated features that are likely to be more predictive, when typical model-building tools are used, than in their raw original state.

Abstract: A system and method are disclosed for furnishing a quote for an insurance product for a user. In one embodiment, the method includes receiving a request from a user for a quote for an insurance product. The request includes an identification of a coverage option and a user identifier. Upon receipt of the request, the system retrieves user credit information based on the user identifier and selects one or more values from the user credit information associated with pre-selected variables related to the selected coverage option. The system then employs the values of the pre-selected variables to calculate a user's insurance credit score for the coverage option.