Process for case-based insurance underwriting suitable for use by an automated system

• US 20030187697A1
• Filed: 06/14/2002
• Published: 10/02/2003
• Est. Priority Date: 12/31/2001
• Status: Active Grant

• Current Assignee: Pacific Life Insurance Company (Pacific Mutual Holding Company)
• Original Assignee: Genworth Financial Incorporated
• Inventors: Bonissone, Piero Patrone, Yang, Dan, Subbu, Rajesh Venkat, Patterson, Angela Neff, Pavese, Marc, Messmer, Richard Paul, Varma, Anil, Mogro-Campero, Antonio, Durham, William Michael, Russell, Diane Marie
• Granted Patent: US 7,844,476 B2
• Time in Patent Office: Days
• US Class Current: 705/4
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A process for at least a partial underwriting of insurance policies is described. Based on the similarity to previous insurance applications, a decision on the current request for underwriting may be made. This decision-making process represents an analogical approach to the placement of an insurance application to an underwriting category, whereby a given insurance application request is compared to previous requests.

Claims

1. A process for underwriting a pending insurance application based on a comparison with at least one of a plurality of previous insurance application underwriting decisions, the process comprising:

receiving a request to underwrite the pending insurance application, where the request includes information about at least one application component;

retrieving a plurality of relevant insurance applications from the plurality of previous insurance application underwriting decisions based on a similarity between the at least one application component and at least one corresponding application component in the retrieved relevant insurance application;

ranking the plurality of retrieved insurance applications according to a level of similarity between the at least one application component and at least one corresponding application component in the retrieved insurance applications;

selecting at least one best insurance application from the plurality of retrieved insurance applications;

adapting a solution to the pending insurance application based on the at least one best insurance application; and

evaluating the solution using a confidence factor, where the confidence factor is based on the reliability of the solution.

2. The process according claim 1, further comprising the step of storing the solution for the pending insurance application in a case memory, wherein the case memory also stores the plurality of previous insurance application underwriting decisions.

3. The process according to claim 1, further comprising the step of transmitting the results of the underwriting decision.

4. The process according to claim 1, wherein the step of retrieving employs at least one fuzzy logic rule to retrieve plurality of previous insurance application underwriting decisions.

5. The process according to claim 4, wherein the at least one fuzzy logic rule is a membership function that interprets the degree to which a value is around a specified parameter.

6. The process according to claim 4, wherein the at least one fuzzy logic rule is a membership function that interprets the degree to which a value is within a core of a specified parameter.

7. The process according to claim 1, wherein the step of ranking the plurality of retrieved insurance applications includes deriving a distribution of the plurality of retrieved insurance applications based on predetermined criteria.

8. A process for rating an application, where the application includes at least one category, the process comprising:

determining a value for the at least one category of the application;

creating a query based on the value of the at least one category;

retrieving at least one case; and

assigning the application a rate classification based on the at least one retrieved case.

9. The process according to claim 8, where a plurality of cases are retrieved, and further comprising the step of generating a distribution of the plurality of cases based on the class rate assigned each of the cases.

10. The process according to claim 8, where a plurality of cases are retrieved, and further comprising the step of determining a minimum similarity value between the plurality of retrieved cases and the application.

11. The process according to claim 8, where a plurality of cases are retrieved, and further comprising the step of generating a pseudo-histogram based on the class rate assigned each of the cases.

12. The process according to claim 8, where the retrieved cases are stored in a case database, and further comprising the step of storing the application in the case database once the rate classification has been assigned.

13. The process according to claim 8, where the application is an application for an insurance application, and where the cases are insurance application cases.

14. A process for rating an insurance application, where the insurance application includes at least one category, the process comprising:

determining a value for the at least one category of the insurance application;

creating a query based on the value of the at least one category;

retrieving at least one insurance application case from an insurance application case database;

assigning the insurance application a rate classification based on the at least one retrieved insurance application case; and

storing the application in the insurance application case database once the rate classification has been assigned.

15. The process according to claim 14, where a plurality of insurance application cases are retrieved, and further comprising the step of generating a distribution of the plurality of insurance application cases based on the class rate assigned each of the insurance application cases.

16. The process according to claim 14, where a plurality of insurance application cases are retrieved, and further comprising the step of determining a minimum similarity value between the plurality of retrieved insurance application cases and the insurance application.

17. The process according to claim 14, where a plurality of insurance application cases are retrieved, and further comprising the step of generating a pseudo-histogram based on the class rate assigned each of the insurance application cases.

18. A computer program stored on a computer readable medium, wherein the computer program causes a computer to perform the steps of:

receiving a request to underwrite the pending insurance application, where the request includes information about at least one application component;

retrieving a plurality of relevant insurance applications from the plurality of previous insurance application underwriting decisions based on a similarity between the at least one application component and at least one corresponding application component in the retrieved relevant insurance application;

ranking the plurality of retrieved insurance applications according to a level of similarity between the at least one application component and at least one corresponding application component in the retrieved insurance applications;

selecting at least one best insurance application from the plurality of retrieved insurance applications;

adapting a solution to the pending insurance application based on the at least one best insurance application; and

evaluating the solution using a confidence factor, where the confidence factor is based on the reliability of the solution.

19. The computer readable medium according to claim 18, further comprising the step of storing the solution for the pending insurance application in a case memory, wherein the case memory also stores the plurality of previous insurance application underwriting decisions.

20. The computer readable medium according to claim 18, further comprising the step of transmitting the results of the underwriting decision.

21. The computer readable medium according to claim 18, wherein the step of retrieving employs at least one fuzzy logic rule to retrieve plurality of previous insurance application underwriting decisions.

22. The computer readable medium according to claim 21, wherein the at least one fuzzy logic rule is a membership function that interprets the degree to which a value is around a specified parameter.

23. The computer readable medium according to claim 21, wherein the at least one fuzzy logic rule is a membership function that interprets the degree to which a value is within a core of a specified parameter.

24. The computer readable medium according to claim 18, wherein the step of ranking the plurality of retrieved insurance applications includes deriving a distribution of the plurality of retrieved insurance applications based on predetermined criteria.

25. A computer program stored on a computer readable medium, wherein the computer program causes a computer to perform the steps of:

determining a value for the at least one category of the application;

creating a query based on the value of the at least one category;

retrieving at least one case; and

assigning the application a rate classification based on the at least one retrieved case.

26. The computer readable medium according to claim 25, where a plurality of cases are retrieved, and further comprising the step of generating a distribution of the plurality of cases based on the class rate assigned each of the cases.

27. The computer readable medium according to claim 25, where a plurality of cases are retrieved, and further comprising the step of determining a minimum similarity value between the plurality of retrieved cases and the application.

28. The computer readable medium according to claim 25, where a plurality of cases are retrieved, and further comprising the step of generating a pseudo-histogram based on the class rate assigned each of the cases.

29. The computer readable medium according to claim 25, where the retrieved cases are stored in a case database, and further comprising the step of storing the application in the case database once the rate classification has been assigned.

30. The computer readable medium according to claim 25, where the application is an application for an insurance application, and where the cases are insurance application cases.

31. A process for underwriting a transaction oriented process based on a comparison with at least one of a plurality of previous transaction underwriting decisions, the process comprising:

receiving a request to underwrite the transaction, where the request includes information about at least one transaction component;

retrieving a plurality of relevant transactions from the plurality of previous transaction underwriting decisions based on a similarity between the at least one transaction component and at least one corresponding transaction component in the retrieved relevant transaction, wherein the step of retrieving employs at least one fuzzy logic rule to retrieve plurality of previous transaction underwriting decisions;

ranking the plurality of retrieved transactions according to a level of similarity between the at least one transaction component and at least one corresponding transaction component in the retrieved transactions;

selecting at least one best transaction from the plurality of retrieved transactions;

adapting a solution to the pending transaction based on the at least one best insurance transaction;

evaluating the solution using a confidence factor, where the confidence factor is based on the reliability of the solution;

storing the solution for the transactions in a case memory, wherein the case memory also stores the plurality of previous transactions underwriting decisions; and

transmitting the results of the underwriting decision.

32. The process according to claim 31, wherein the at least one fuzzy logic rule is a membership function that interprets the degree to which a value is around a specified parameter.

33. The process according to claim 31, wherein the at least one fuzzy logic rule is a membership function that interprets the degree to which a value is within a core of a specified parameter.

34. The process according to claim 31, wherein the step of ranking the plurality of retrieved transactions includes deriving a distribution of the plurality of retrieved transactions based on predetermined criteria.