SYSTEM AND METHOD FOR UTILIZING INTERRELATED COMPUTERIZED PREDICTIVE MODELS

• US 20080154651A1
• Filed: 12/20/2007
• Published: 06/26/2008
• 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.
• Granted Patent: US 7,945,497 B2
• Time in Patent Office: Days
• US Class Current: 705/4
• 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;

first and second computerized predictive models, wherein an output of the first predictive model serves as an input parameter to the second computerized predictive model and an output of the second computerized predictive model serves as an input to the first computerized model; and

a business logic module configured to process the accepted data to i) determine a recommended set of policy parameters for an insured by executing the first and second predictive models based on the accepted data, and ii) output the recommended set of policy parameters to the user via the user interface.

2. The system of claim 1, comprising a data capture module for extracting input parameters for the first and second computerized predictive models.

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 module to serve as an input to at least one of the first and second computerized predictive models.

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 logic module to serve as an input to at least one of the first and second computerized predictive models.

6. The system of claim 2, wherein the business logic module comprises a rule engine configured to i) identify parameters of the first and second computerized predictive models for which additional data would improve performance of the respective first and second computerized predictive models 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 module processes the accepted data to determine and output a workflow component for the insurance request by executing the first and second computerized predictive models.

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 first and second computerized predictive models.

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

11. The system of claim 9, wherein for each recommended set, the business logic module determines and outputs at least one of a price component and a workflow component associated with the respective set by executing the first and second computerized predictive models.

19. The method of claim 11, wherein the workflow component comprises an underwriting review process step.

22. The method of claim 19, comprising, for each recommended set, determining and outputting, by the business logic module, at least one of a price component and a workflow component associated with the respective set by executing the first and second computerized predictive models.

12. A method for processing an insurance request comprising:

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

processing, by a business logic module, the accepted data to determine a recommended set of policy parameters for an insured by executing first and second predictive models based on the accepted data, wherein an output of the first predictive model serves as an input parameter to the second computerized predictive model and an output of the second computerized predictive model serves as an input to the first computerized model; and

outputting, by the business logic module, the recommended set of policy parameters to the user via the user interface.

13. The method of claim 12, comprising extracting, by a data capture module, input parameters for the first and second computerized predictive models.

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 first and second computerized predictive models.

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 module to serve as an input to at least one of the first and second computerized predictive models.

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 first and second computerized predictive models.

17. The method of claim 13, comprising:

identifying, by the business logic module, parameters of the first and second computerized predictive models for which additional data would improve performance of the respective first and second computerized predictive models, and

outputting, by the business logic module, 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 module, the accepted data to determine and output a workflow component for the insurance request by executing the first and second computerized predictive models.

20. The method of claim 12, comprising processing, by the business logic module, the accepted data to determine and output a price component for the insurance request by executing the first and second computerized predictive models.

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

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:

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

processing, by a business logic module, the accepted data to determine a recommended set of policy parameters for an insured by executing first and second predictive models based on the accepted data, wherein an output of the first predictive model serves as an input parameter to the second computerized predictive model and an output of the second computerized predictive model serves as an input to the first computerized model; and

outputting, by the business logic module, the recommended set of policy parameters to the user via the user interface.

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 module, parameters of the first and second computerized predictive models for which additional data would improve performance of the respective first and second computerized predictive models, and

output, by the business logic module, 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 module, the accepted data to determine and output a workflow component for the insurance request by executing the first and second computerized predictive models.

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 module, the accepted data to determine and output a price component for the insurance request by executing the first and second computerized predictive models.

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 module, 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 module, at least one of a price component and a workflow component associated with the respective set by executing the first and second computerized predictive models.

29. A system for processing an insurance request, comprising:

a data capture module configured to receive data from a user and at least one of a third party data source and a sensor monitoring a condition of a property to be insured;

a business logic module configured to process the received data with a computerized predictive model to determine a recommended set of policy parameters for an insured and outputting the recommended set of policy parameters for presentation to the user.

30. The system of claim 29, wherein the business logic module determines and outputs for presentation to the user a plurality of sets of recommended policy parameters.

31. The system of claim 30, wherein the business logic module determines and outputs for presentation to the user, for each of the respective plurality of sets of recommended policy parameters, at least one of a workflow component and a pricing component.

32. A method for processing an insurance request, comprising:

receiving, by a data capture module, data from a user and at least one of a third party data source and a sensor monitoring a condition of a property to be insured;

processing, by a business logic module, the received data with a computerized predictive model to determine a recommended set of policy parameters for an insured, and

outputting, by the business logic module, the recommended set of policy parameters for presentation to the user.

33. The method of claim 32, comprising determining and outputting for presentation to the user a plurality of sets of recommended policy parameters.

34. The method of claim 33, comprising determining and outputting for presentation to the user, for each of the respective plurality of sets of recommended policy parameters, at least one of a workflow component and a pricing component.

35. A system for processing an insurance request, comprising:

a data capture module for receiving data from a user and at least one of a third party data source and a sensor monitoring a condition of a property to be insured; and

a business logic module that includes a predictive model configured to dynamically determine a set of questions for presentation to the user;

a user interface for presenting the set of questions to the user.

36. The system of claim 35, wherein the business logic module determines the set of questions based at least in part on data other than the data received from the user.

37. The method of claim 35, wherein the business logic module determines the set of questions based on responses to questions included in the set of questions.