Commercial insurance scoring system and method

Abstract

A quantitative system and method that leverages data sources external to an insurance company to generate a statistical model that may be used to predict insurance coverage profitability. The system and method can predict profitability on a prospective basis regardless of the internal data and business practices of a particular insurance company.

What is claimed is: 
     
         1 . A method for predicting the profitability of insurance coverage, the method comprising:
 using at least one data processing device:
 determining predictive variables based on variables included in data, the predictive variables being ones of the variables included in the data that are predictive of insurance coverage profitability, the predictive variables including at least one derived variable that is one of a combination of and derived from the variables included in the data; 
 creating a statistical model based on the predictive variables; 
 using the model, calculating a score for at least one insurance coverage record; and 
 using the score to predict the profitability of the at least one insurance coverage record. 
   
     
     
         2 . The method of  claim 1 , wherein the data is from at least one external data source. 
     
     
         3 . The method of  claim 2 , wherein determining predictive variables includes associating normalized historical premium and loss data with the at least one external data source. 
     
     
         4 . The method of  claim 1 , wherein creating the statistical model is effected using at least one multivariate method. 
     
     
         5 . The method of  claim 1 , wherein the at least one insurance coverage record is a commercial insurance policy. 
     
     
         6 . A non-transitory medium storing computer executable program logic to:
 determine predictive variables based on variables included in data, the predictive variables being ones of the variables included in the data that are predictive of insurance coverage profitability, the predictive variables including at least one derived variable that is one of a combination of and derived from the variables included in the data;   create a statistical model based on the predictive variables;   using the model, calculate a score for at least one insurance coverage record; and   predict the profitability of the at least one insurance coverage record based on the score.   
     
     
         7 . The medium of  claim 6 , wherein the data is from at least one external data source. 
     
     
         8 . The medium of  claim 7 , wherein determining the predictive variables includes associating normalized historical premium and loss data with the at least one external data source. 
     
     
         9 . The medium of  claim 6 , wherein creating the statistical model includes using at least one multivariate method. 
     
     
         10 . The medium of  claim 6 , wherein the at least one insurance coverage record is a commercial insurance policy.