System and method for predicting and responding to likelihood of volatility

• US 20080147448A1
• Filed: 12/19/2007
• Published: 06/19/2008
• Est. Priority Date: 12/19/2006
• 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: Mohanty, Natalie, Goddu, Gregory P., Maurer, Kathleen F., McLaughlin, Kelly J., Belhe, Upendra D.
• Granted Patent: US 8,359,209 B2
• Time in Patent Office: Days
• US Class Current: 705/4
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

The invention relates generally to data analysis, and to systems and methods for the computation of the volatility of a loss. The system comprises a module for receiving a data parameter, a database for storing the parameter, a computerized predictive model, and a business logic processor for executing the predictive model. The volatility is used to, among other things, determine an appropriate work flow for handling the loss.

Claims

1. A system for analyzing data comprising:

an input module for receiving at least one parameter corresponding to a characteristic of an insurance claim;

a database for storing the parameter received by the input module;

a computerized predictive model for determining a volatility indicator for the insurance claim based on the parameter; and

one or more business logic processors for;

executing the predictive models; and

processing the insurance claim based upon the volatility indicator determined by the computerized predictive model.

2. The system of claim 1, wherein processing the insurance claim comprises adjusting a collective reserve for a group of claims having similar volatility indicators based on the volatility of the claims in the group.

3. The system of claim 1, wherein the computerized predictive model is configured for updating itself after at least one new insurance claim cost has been determined.

4. The system of claim 1, wherein the one or more business logic processors are configured for recommending a course of treatment for the claim based on its associated volatility indicator.

5. The system of claim 1, wherein the one or more business logic processors are configured for:

detecting a change in a volatility indicator associated with a claim, and

recommending a course of treatment for the claim based on the detected change.

6. The system of claim 1, wherein processing the insurance claim comprises making a workflow determination for the insurance claim based upon the volatility indicator.

7. The system of claim 6, wherein the workflow determination comprises an assignment of the insurance claim to an employee from a plurality of employees to handle the claim based upon the volatility indicator.

8. The system of claim 6, wherein the workflow determination comprises a selection of an investigation level for the insurance claim based upon the volatility indicator.

9. The system of claim 8, wherein the selection of the investigation level comprises determining whether to engage a private investigator to investigate the claim.

10. The system of claim 8, wherein the selection of the investigation level comprises determining whether to engage an independent medical examiner to investigate the claim.

11. The system of claim 6, wherein the workflow determination comprises a selection of a level of medical review for the insurance claim based upon the volatility indicator.

12. The system of claim 6, wherein the workflow determination comprises a selection of a level of medical care for the insurance claim based on the volatility indicator.

13. The system of claim 1, wherein:

the database is configured such that the at least one parameter may be updated;

at least one of the one or more processors is configured to re-execute the computerized predictive model in response to the at least one parameter being updated to determine a new volatility indicator; and

at least one of the one or more processors is configured to process the insurance claim based upon the new volatility indicator.

14. The system of claim 1, wherein the computerized predictive model is generated based at least in part on an analysis of medical spending costs for a plurality of claims.

15. The system of claim 1, wherein the computerized predictive model determines the volatility indicator at least in part on data extracted from unstructured text by a text mining application.

16. The system of claim 1, wherein the computerized predictive model comprises a collection of decision trees.

17. The system of claim 1, wherein at least one of the one or more business logic processors is configured for training the computerized predictive model.

18. The system of claim 1, wherein the least one of the one or more business logic processor is configured to:

segment insurance claims based on their respective volatility indicators into groups; and

set unassigned reserves for each group as a function of the volatility of insurance claims in the respective segment.

19. The system of claim 18, wherein the at least one of the one or more business logic processors is configured to set surplus reserves for each segment as a function of the volatility of insurance claims in the respective segment.

20. A system for analyzing data comprising:

a database for storing;

a plurality of characteristics for an insurance-seeking company and for a plurality of insured companies, and

insurance claims histories for the plurality of insured companies;

a computerized predictive model trained on the data stored in the database for the plurality of insured companies to detect companies likely to have volatile claims; and

one or more business logic processors for;

underwriting the insurance-seeking company based on the plurality of parameters received for the insurance-seeking company and the computerized predictive model, and

outputting an underwriting decision based on the underwriting.

21. The system of claim 20, wherein the underwriting decision comprises a premium price.

22. The system of claim 20, wherein the underwriting decision comprises a classification.

23. The system of claim 20, wherein the underwriting decision comprises one of a decision to extend coverage, a decision to deny coverage, a decision to renew coverage, and a decision to adjust an underwriting workflow process.

24. A method for analyzing data comprising:

receiving by an input module at least one parameter corresponding to a characteristic of an insurance claim;

storing by a processor the parameter in a database;

executing by the processor a computerized predictive model based at least in part on the parameter to determine a volatility indicator for the insurance claim; and

processing the insurance claim based upon the volatility indicator determined by the computerized predictive model.

25. The method of claim 24, wherein processing the insurance claim comprises adjusting a collective reserve for a group of claims having similar volatility indicators based on the volatility of the claims in the group.

26. The method of claim 24, wherein the computerized predictive model is configured for updating itself after at least one new insurance claim cost has been determined.

27. The method of claim 24, further comprising recommending a course of treatment for the claim based on its associated volatility indicator.

28. The method of claim 24, further comprising:

detecting a change in a volatility indicator associated with a claim, and

recommending a course of treatment for the claim based on the detected change.

29. The method of claim 24, wherein processing the insurance claim comprises making a workflow determination for the insurance claim based upon the volatility indicator.

30. The method of claim 29, wherein the workflow determination comprises an assignment of the insurance claim to an employee from a plurality of employees to handle the claim based upon the volatility indicator.

31. The method of claim 29, wherein the workflow determination comprises a selection of an investigation level for the insurance claim based upon the volatility indicator.

32. The method of claim 31, wherein the selection of the investigation level comprises determining whether to engage a private investigator to investigate the claim.

33. The method of claim 31, wherein the selection of the investigation level comprises determining whether to engage an independent medical examiner to investigate the claim.

34. The method of claim 29, wherein the workflow determination comprises a selection of a level of medical review for the insurance claim based upon the volatility indicator.

35. The method of claim 29, wherein the workflow determination comprises a selection of a level of medical care for the insurance claim based on the volatility indicator.

36. The method of claim 24, further comprising:

updating the parameter stored in the database;

re-executing the computerized predictive model in response to the parameter update to determine a new volatility indicator; and

processing the insurance claim based upon the new volatility indicator.

37. The method of claim 24, wherein the computerized predictive model is generated based at least in part on an analysis of medical spending costs for a plurality of claims.

38. The method of claim 24, wherein the computerized predictive model determines the volatility indicator at least in part on data extracted from unstructured text by a text mining application.

39. The method of claim 24, wherein the computerized predictive model comprises a collection of decision trees.

40. The method of claim 24, wherein the computerized predictive model is generated from training data.

41. The method of claim 24, further comprising:

segmenting insurance claims based on their respective volatility indicators into groups; and

setting unassigned reserves for each group as a function of the volatility of insurance claims in the respective segment.

42. The method of claim 41, further comprising setting surplus reserves for each segment as a function of the volatility of insurance claims in the respective segment.

43. A method for analyzing data comprising:

storing by a processor in a database a plurality of parameters for an insurance-seeking company and for a plurality of insured companies, and insurance claims histories for the plurality of insured companies;

training by a processor a computerized predictive model on the data stored in the database for the plurality of insured companies to detect companies likely to have volatile claims;

underwriting by a processor the insurance-seeking company based on the plurality of parameters received for the insurance-seeking company and the computerized predictive model; and

outputting an underwriting decision based on the underwriting.

44. The method of claim 43, wherein the underwriting decision comprises a premium price.

45. The method of claim 43, wherein the underwriting decision comprises a classification.

46. The method of claim 43, wherein the underwriting decision comprises one of a decision to extend coverage, a decision to deny coverage, a decision to renew coverage, and a decision to adjust an underwriting workflow process.

47. A computer-readable medium encoded with machine-readable instructions for analyzing data, the machine-readable instructions comprising:

receiving at least one parameter corresponding to a characteristic of an insurance claim;

storing the parameter in a database;

executing a computerized predictive model based at least in part on the parameter to determine a volatility indicator for the insurance claim; and

processing the insurance claim based upon the volatility indicator determined by the computerized predictive model.

48. The computer-readable medium of claim 47, wherein processing the insurance claim comprises making a workflow determination for the insurance claim based upon the volatility indicator.

49. The computer-readable medium of claim 47, wherein the computerized predictive model comprises a collection of decision trees.

50. A computer-readable medium encoded with machine-readable instructions for analyzing data, the machine-readable instructions comprising:

storing in a database a plurality of parameters for an insurance-seeking company and for a plurality of insured companies, and insurance claims histories for the plurality of insured companies;

training a computerized predictive model on the data stored in the database for the plurality of insured companies to detect companies likely to have volatile claims;

underwriting the insurance-seeking company based on the plurality of parameters received for the insurance-seeking company and the computerized predictive model; and

outputting an underwriting decision based on the underwriting.

51. The computer-readable medium of claim 50, wherein the underwriting decision comprises one of a decision to extend coverage, a decision to deny coverage, a decision to renew coverage, and a decision to adjust an underwriting workflow process.

52. The computer-readable medium of claim 50, wherein the computerized predictive model comprises a collection of decision trees.