System and method for processing data relating to insurance claim volatility

• US 8,798,987 B2
• Filed: 10/23/2013
• Issued: 08/05/2014
• 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: McLaughlin, Kelly J., Belhe, Upendra D., Goddu, Gregory P., Mohanty, Natalie, Mauer, Kathleen F.
• Primary Examiner(s): Oyebisi, Ojo O
• Application Number:
  US14/061,283
• Publication Number:
  US 20140046705A1
• Time in Patent Office: 286 Days
• Field of Search: 705/4, 705/8, 705/35, 705/2
• US Class Current: 704/4
• 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 computer system for processing data relating to a volatility of an insurance claim, comprising:

an input device coupled to a client terminal and configured to;

receive at least one parameter corresponding to a characteristic of the insurance claim;

a data storage device coupled to the input device and configured to;

store the at least one parameter received by the input device;

one or more memories configured to;

store program instructions;

one or more business computer processors coupled to the one or more memories and to the data storage device, wherein the one or more business computer processors, upon execution of the program instructions, are configured to;

estimate, based at least on the at least one parameter, using at least one computerized model, a likelihood the insurance claim will exhibit increased volatility, volatility being indicative of a likelihood of an actual total resolution cost of the insurance claim differing from a predicted total resolution cost of the insurance claim;

generate a data file for the insurance claim including the estimate of the likelihood the insurance claim will exhibit increased volatility; and

transmit the data file, including the estimate of the likelihood the insurance claim will exhibit increased volatility, to the client terminal.

2. The system of claim 1, wherein the one or more memories are further configured to store a model for estimating the likelihood an insurance claim will exhibit increased volatility and wherein the one or more business computer processors being configured to estimate the increased volatility comprises the one or more business computer processors being configured to execute the model.

3. The system of claim 2, wherein the one or more business computer processors are configured to, in executing the model for estimating the likelihood the insurance claim will exhibit increased volatility, determine a volatility likelihood value representative of the estimate of the likelihood an insurance claim will exhibit increased volatility and wherein the estimate of the likelihood the insurance claim will exhibit increased volatility included in the data file comprises the volatility likelihood value.

4. The system of claim 3, wherein the volatility likelihood value comprises one of a raw score, a probability value, a tier value, or a relative value comparing the likelihood the insurance claim will exhibit increased volatility with a likelihood that other pending insurance claims will exhibit increased volatility.

5. The system of claim 4, wherein the relative value comprises an absolute ranking of the insurance claim with respect to other pending insurance claims or a ranking of the insurance claim with respect to a particular tranche of insurance claims.

6. The system of claim 3, further comprising:

one or more workflow memories configured to;

store workflow data pertaining to one or more of claim handlers, supervisors, medical reviewers, medical providers, medical provider supervisors, private investigators, and vendors; and

store workflow program instructions; and

one or more workflow processors coupled to the one or more workflow memories, wherein the one or more workflow processors, upon execution of the workflow program instructions, are configured to;

assign a non-compensatory expense tolerance level to the insurance claim based on the volatility likelihood value.

7. The system of claim 2, wherein the model is a computerized predictive model comprising at least one of a linear regression model, a neural network, a decision tree model, or a collection of decision tree models.

8. A computer-implemented method for processing data for analyzing volatility of an insurance claim comprising:

receiving by an input device coupled to a client terminal at least one parameter corresponding to a characteristic of the insurance claim;

storing in a data storage device the at least one parameter;

estimating, by one or more business computer processors, using at least one computerized model, based at least on the at least one parameter, a likelihood the insurance claim will exhibit increased volatility, volatility indicating a likelihood of an actual total resolution cost of the insurance claim differing from a predicted total resolution cost of the insurance claim;

generating, by the one or more business computer processors, a data file for the insurance claim including the estimated likelihood the insurance claim will exhibit increased volatility, and

transmitting the data file to the client terminal.

9. The computer-implemented method of claim 8, wherein estimating the likelihood an insurance claim will exhibit increased volatility comprises executing by the one or more computer processors a model for estimating the likelihood the insurance claim will exhibit increased volatility.

10. The computer-implemented method of claim 9, wherein the executing the model for estimating the likelihood the insurance claim will exhibit increased volatility comprises determining a volatility likelihood value representative of the estimate of the likelihood the insurance claim will exhibit increased volatility and wherein the estimate of the likelihood the insurance claim will exhibit increased volatility included in the data file comprises the volatility likelihood value.

11. The computer-implemented method of claim 10, wherein the volatility likelihood value comprises one of a raw score, a probability value, a tier value, or a relative value comparing the likelihood the insurance claim will exhibit increased volatility with a likelihood that other pending insurance claims will exhibit increased volatility.

12. The computer-implemented method of claim 11, wherein the relative value comprises an absolute ranking of the insurance claim with respect to other pending insurance claims or a ranking of the insurance claim with respect to a particular tranche of insurance claims.

13. The computer-implemented method of claim 10, further comprising:

storing in one or more workflow memories, data pertaining to one or more of claim handlers, supervisors, medical reviewers, medical providers, medical provider supervisors, private investigators, and vendors; and

assigning, by one or more workflow processors based on the data in the one or more workflow memories, a non-compensatory expense tolerance level to the insurance claim based on the volatility likelihood value.

14. The computer-implemented method of claim 10, further comprising identifying, by an expert system coupled to the one or more business computer processors, appropriate treatments for a claimant under the insurance claim based on the volatility likelihood value or a change in the volatility likelihood value.

15. A non-transitory computer readable medium having stored therein instructions that, upon execution, cause one or more computer processors to:

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

store in a data storage device the at least one parameter;

estimate, based at least on the at least one parameter, using at least one computerized model, a likelihood the insurance claim will exhibit increased volatility, volatility being indicative of a likelihood of an actual total resolution cost of the insurance claim differing from a predicted total resolution cost of the insurance claim;

generate a data file for the insurance claim including the estimate of the likelihood the insurance claim will exhibit increased volatility; and

transmit the data file to the client terminal.

16. The non-transitory computer readable medium of claim 15, wherein the instructions that, upon execution, cause the one or more computer processors to estimate the likelihood the insurance claim will exhibit increased volatility, comprise instructions for executing a model configured to estimate the increased volatility.

17. The non-transitory computer readable medium of claim 16, wherein the model configured to estimate the likelihood the insurance claim will exhibit increased volatility determines a volatility likelihood value representative of the estimate of the likelihood the insurance claim will exhibit increased volatility, and wherein the estimate of the likelihood the insurance claim will exhibit increased volatility included in the data file comprises the volatility likelihood value.

18. The non-transitory computer readable medium of claim 17, wherein the volatility likelihood value comprises one of a raw score, a probability value, a tier value, or a relative value comparing the likelihood the insurance claim will exhibit increased volatility with a likelihood that other pending insurance claims will exhibit increased volatility.

19. The non-transitory computer readable medium of claim 17, wherein the instructions, upon execution, further cause the one or more computer processors to:

store in one or more memories, data pertaining to one or more of claim handlers, supervisors, medical reviewers, medical providers, medical provider supervisors, private investigators, and vendors; and

assign based on the data in the one or more workflow memories, a non-compensatory expense tolerance level to the insurance claim based on the volatility likelihood value.

20. The non-transitory computer readable medium of claim 17, wherein the instructions, upon execution, further cause the one or more computer processors to:

identify appropriate treatments for a claimant based on the volatility likelihood value or a change in the volatility likelihood value.