System and method for utilizing interrelated computerized predictive models

• US 7,945,497 B2
• Filed: 12/20/2007
• Issued: 05/17/2011
• Est. Priority Date: 12/22/2006
• Status: Active Grant

• Current Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Original Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Inventors: Murphy, Theresa C., Besman, Eric, Kenefick, Timothy P.
• Primary Examiner(s): Apple; Kirsten S
• Assistant Examiner(s): Basit; Abdul
• Application Number:
  US11/961,380
• Publication Number:
  US 20080154651A1
• Time in Patent Office: 1,244 Days
• Field of Search: 705/35, 705/4
• US Class Current: 705/35
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

The invention relates to a system for handling insurance requests, such as new coverage applications, renewal applications, and insurance quote requests. The system includes at least two computerized predictive models whose outputs each serve as inputs to the other. A business logic module is included in the system to process insurance requests with the predictive models to determine one or more sets of recommended policy parameters for the user and to output the determination to the user via a user interface. In various embodiments, the predictive models also output workflow components (such as underwriting workflow components) and price components (such as premium prices) corresponding to output suggested sets of coverage parameters.

Claims

1. A system for processing an insurance request comprising:

a user interface for accepting data related to an insurance request from a user;

a business logic processor configured to process the accepted data to i) determine a recommended set of policy parameters for an insured, and ii) output the recommended set of policy parameters to the user via the user interface, wherein the business logic processor comprises;

a computerized coverage recommendation predictive model which is configured to determine and output a policy parameter recommendation based on the accepted data;

a computerized pricing predictive model which is configured to receive the policy parameter recommendation as an input, determine a price corresponding to an insurance policy including the received policy parameter recommendation based on the accepted data, and output the determined price into the coverage recommendation predictive model;

wherein the coverage recommendation predictive model is further configured to determine and output an updated policy parameter recommendation based on the price output by the pricing predictive model, the accepted data, and a previously output policy parameter recommendation.

2. The system of claim 1, comprising a data capture module for extracting input parameters for the computerized coverage recommendation predictive model and computerized pricing predictive model.

3. The system of claim 2, wherein the data capture module comprises a text mining application for extracting structured data from unstructured text.

4. The system of claim 2, wherein the data capture module is configured to obtain data from a third-party data source and output the data to the business logic processor to serve as an input to at least one of the computerized coverage recommendation predictive model and computerized pricing predictive model.

5. The system of claim 2, wherein the data capture module is configured to obtain data from at least one sensor monitoring the use or condition of a property to be insured and output the data to the business processor to serve as an input to at least one of the computerized coverage recommendation predictive model and computerized pricing predictive model.

6. The system of claim 2, wherein the business logic processor comprises a rule engine configured to i) identify parameters of the computerized coverage recommendation predictive model and computerized pricing predictive model for which additional data would improve performance of the respective computerized coverage recommendation predictive model and computerized pricing predictive model and ii) output the identified parameters to at least one of the user interface and the data capture module.

7. The system of claim 1, wherein the business logic processor processes the accepted data to determine and output a workflow component for the insurance request by executing the computerized coverage recommendation predictive model and computerized pricing predictive model.

8. The system of claim 1, wherein the workflow component comprises an underwriting review process step.

9. The system of claim 1, wherein the business logic module processes the accepted data to determine and output a price component for the insurance request by executing the computerized coverage recommendation predictive model and computerized pricing predictive model.

10. The system of claim 1, wherein the business logic processor outputs a plurality of recommended sets of policy parameters to the user via the user interface.

11. The system of claim 10, wherein for each recommended set, the business logic processor determines and outputs at least one of a price component and a workflow component associated with the respective set by executing the computerized coverage recommendation predictive model and computerized pricing predictive model.

12. A method for processing an insurance request comprising:

providing a user interface for accepting data related to an insurance request from a user;

processing the insurance request via a business logic processor configured to process the accepted data to i) determine a recommended set of policy parameters for an insured, and ii) output the recommended set of policy parameters to the user via the user interface,

wherein processing the insurance request comprises;

processing the accepted data by a computerized coverage recommendation predictive model configured to determine and output a policy parameter recommendation based on the accepted data;

processing the output policy parameter recommendation by a computerized pricing predictive model which is configured to receive the policy parameter recommendation as an input, determine a price corresponding to an insurance policy including the received policy

parameter recommendation based on the accepted data, and output the determined price into the coverage recommendation predictive model;

receiving, by the computerized coverage recommendation predictive model, the determined price;

determining and outputting, by the computerized coverage recommendation predictive model, an updated policy parameter recommendation based on the price output by the computerized pricing predictive model, the accepted data, and a previously output policy parameter recommendation.

13. The method of claim 12, comprising extracting, by a data capture module, input parameters for the computerized coverage recommendation predictive model and computerized pricing predictive model.

14. The method of claim 13, comprising:

obtaining, by the data capture module, data from a third-party data source; and

outputting, by the data capture module, the obtained data to serve as an input to at least one of the computerized coverage recommendation predictive model and computerized pricing predictive model.

15. The method of claim 13, comprising:

obtaining, by the data capture module, data from at least one sensor monitoring the use or condition of a property to be insured, and

outputting, by the data capture module, the obtained data to the business logic processor to serve as an input to at least one of the computerized coverage recommendation predictive model and computerized pricing predictive model.

16. The method of claim 12, comprising extracting, by a text mining application, data from unstructured text and outputting the extracted data to at least one of the computerized coverage recommendation predictive model and computerized pricing predictive model.

17. The method of claim 13, comprising:

identifying, by the business logic processor, parameters of the computerized coverage recommendation predictive model and computerized pricing predictive model for which additional data would improve performance of the respective computerized coverage recommendation predictive model and computerized pricing predictive model, and

outputting, by the business logic processor, the identified parameters to at least one of the user interface and the data capture module.

18. The method of claim 12, comprising processing, by the business logic processor, the accepted data to determine and output a workflow component for the insurance request by executing the computerized coverage recommendation predictive model and computerized pricing predictive model.

19. The method of claim 12, wherein the workflow component comprises an underwriting review process step.

20. The method of claim 12, comprising processing, by the business logic processor, the accepted data to determine and output a price component for the insurance request by executing the computerized coverage recommendation predictive model and computerized pricing predictive model.

21. The method of claim 12, comprising outputting, by the business logic processor, a plurality of recommended sets of policy parameters to the user via the user interface.

22. The method of claim 21, comprising, for each recommended set, determining and outputting, by the business logic processor, at least one of a price component and a workflow component associated with the respective set by executing the computerized coverage recommendation predictive model and computerized pricing predictive model.

23. A computer-readable medium storing computer-executable instructions, which, when executed by a processor, cause the processor to carry out a method of processing an insurance request, the method comprising:

providing a user interface for accepting data related to an insurance request from a user;

processing the insurance request via a business logic processor configured to process the accepted data to i) determine a recommended set of policy parameters for an insured, and ii) output the recommended set of policy parameters to the user via the user interface, wherein processing the insurance request comprises;

processing the accepted data by a computerized coverage recommendation predictive model configured to determine and output a policy parameter recommendation based on the accepted data;

processing the output policy parameter recommendation by a computerized pricing predictive model which is configured to receive the policy parameter recommendation as an input, determine a price corresponding to an insurance policy including the received policy parameter recommendation based on the accepted data, and output the determined price into the coverage recommendation predictive model;

receiving, by the computerized coverage recommendation predictive model, the determined price;

determining and outputting, by the computerized coverage recommendation predictive model, an updated policy parameter recommendation based on the price output by the computerized pricing predictive model, the accepted data, and a previously output policy parameter recommendation.

24. The computer readable medium of claim 23, storing instructions, which when executed by the processor, cause the processor to:

identify, by the business logic processor, parameters of the computerized coverage recommendation predictive model and computerized pricing predictive model for which additional data would improve performance of the respective computerized coverage recommendation predictive model and computerized pricing predictive model, and

output, by the business logic processor, the identified parameters to at least one of the user interface and a data capture module.

25. The computer readable medium of claim 23, storing instructions, which when executed by the processor, cause the processor to process, by the business logic processor, the accepted data to determine and output a workflow component for the insurance request by executing the computerized coverage recommendation predictive model and computerized pricing predictive model.

26. The computer readable medium of claim 23, storing instructions, which when executed by the processor, cause the processor to process, by the business logic processor, the accepted data to determine and output a price component for the insurance request by executing the computerized coverage recommendation predictive model and computerized pricing predictive model.

27. The computer readable medium of claim 23, storing instructions, which when executed by a processor, cause the processor to output, by the business logic processor, a plurality of recommended sets of policy parameters to the user via the user interface.

28. The computer readable medium of claim 27, storing instructions, which when executed by a processor, cause the processor to, for each recommended set, determine and output, by the business logic processor, at least one of a price component and a workflow component associated with the respective set by executing the computerized coverage recommendation predictive model and computerized pricing predictive model.