Systems and methods for assessing the potential for fraud in business transactions

• US 7,827,045 B2
• Filed: 02/28/2005
• Issued: 11/02/2010
• Est. Priority Date: 11/05/2003
• Status: Active Grant

• Current Assignee: Computer Sciences Corporation (DXC Technology Company)
• Original Assignee: Computer Sciences Corporation (DXC Technology Company)
• Inventors: Rogers, James Lewis, Mtshali, Progress Qhaqhi Thabani, Madill, Robert P. Jr., Barger, Thomas Glenn
• Primary Examiner(s): Kyle; Charles R
• Assistant Examiner(s): WEIS, SAMUEL
• Application Number:
  US11/068,503
• Publication Number:
  US 20050276401A1
• Time in Patent Office: 2,073 Days
• Field of Search: 705/4
• US Class Current: 705/4
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

Methods and systems are provided for assessing the potential for fraud of an insurance claim. In some embodiments, request data may be provided to a computer system. In some embodiments, at least one fraud potential indicator may be assessed to the request data from at least one comparison of at least one request data element to at least one fraud model. In some embodiments, a fraud potential indicator may be an estimate of the potential for fraud in an insurance claim. In some embodiments, at least one fraud potential indicator for request data may be assessed based on at least one comparison of at least one request data element to additional insurance data. Some embodiments may include assessing at least one fraud potential indicator for request data based on at least one fraud potential indicator.

Claims

1. A method of managing insurance claim requests comprising:

accessing, by a user system, an insurance request processing computer system;

transmitting one or more insurance claim requests relating to an accident to the insurance request processing computer system, wherein at least one of the insurance claim requests comprises one or more request data elements;

assessing, by the insurance request processing computer system, at least one fraud potential indicator for an insurance claim request relating to the accident, wherein the at least one fraud potential indicator comprises a numerical estimate of a probability of fraud in the insurance claim request, wherein the assessing of the at least one fraud potential indicator comprises;

comparing, by the insurance request processing computer system, at least one of the request data elements to one or more fraud models comprising at least one historical fraud pattern derived from insurance claims that have been proven fraudulent, wherein comparison of the at least one of the request data elements to one or more fraud models comprises searching for request patterns in the one or more request data elements that are similar to the at least one historical fraud pattern; and

applying, by the insurance request processing computer system, one or more business rules to at least one of the request data elements, the application of the one or more business rules comprising;

computing one or more numerical values for the at least one fraud potential indicator using one or more formulas, wherein computing at least one of the numerical values for the at least one fraud potential indicator comprises;

multiplying a loss type multiplier by at least one other numerical value to produce the numerical value for the at least one fraud potential indicator, wherein the value of the loss type multiplier varies depending on the type of accident; and

automatically assigning the insurance claim request if one or more fraud potential indicators is within a fraud range.

2. The method of claim 1, wherein the insurance claim request is automatically assigned to an adjuster.

3. The method of claim 1, wherein the insurance claim request is automatically assigned to an investigator.

4. The method of claim 1, wherein the insurance claim request is automatically assigned to a special investigative unit.

5. The method of claim 1, further comprising transmitting a report to an assigned investigator, wherein the report comprises the fraud potential indicator associated with the insurance claim request.

6. The method of claim 1, further comprising transmitting a report to an assigned investigator, wherein the report comprises:

the fraud potential indicator; and

one or more reasons the insurance claim request was transferred to the assigned investigator.

7. The method of claim 1, wherein the insurance claim request is automatically assigned at least partially based on preferences of an investigator.

8. The method of claim 1, wherein the insurance claim request is automatically assigned at least partially based on where a request was filed.

9. The method of claim 1, wherein the insurance claim request comprises an insurance claim, and wherein the insurance claim request is automatically assigned at least partially based on the value of the insurance claim.

10. The method of claim 1, wherein the insurance claim request an automobile insurance claim, and wherein the insurance claim request is automatically assigned at least partially based on experiences of an investigator.

11. The method of claim 1, wherein the insurance claim request is automatically assigned at least partially based on the type of insurance claim request.

12. The method of claim 1, wherein the insurance claim request is automatically assigned at least partially based on the availability of an investigator.

13. The method of claim 1, wherein the insurance claim request is automatically assigned at least partially based on predetermined set of skills an investigator needs to investigate the insurance claim request.

14. The method of claim 1, wherein automatically assigning the insurance claim request to an investigator comprises:

comparing experiences of available investigators to predetermined skills required to investigate the insurance claim request; and

selecting an investigator, wherein the investigator selected has the skills required to investigate the insurance claim request.

15. The method of claim 1, wherein automatically assigning the request if one or more fraud potential indicators is within a fraud range comprises:

assigning the request as non-fraudulent if the fraud potential indicator is within a fraud range below a fraud threshold value;

assigning the request to a first level of review if the fraud potential indicator is within a first fraud range above the fraud threshold value; and

assigning the request to a second level of review if the fraud potential indicator is within a second fraud range that is different from the first fraud range and above the fraud threshold value.

16. The method of claim 1, wherein automatically assigning the request if one or more fraud potential indicators is within a fraud range comprises:

assigning for payment an insurance claim associated with the request if the fraud potential indicator is within a fraud range below a fraud threshold value;

assigning the request to a first level of review by a claims adjuster if the fraud potential indicator is within a first fraud range above the fraud threshold value;

assigning the request to a second level of review by an investigator if the fraud potential indicator is within a second fraud range that is different from the first fraud range and is indicative of a higher potential for fraud than the first range; and

assigning the request to a third level of review by a special investigative unit if the fraud potential indicator is within a third fraud range that is different from the first range and the second fraud range and is indicative of a higher potential for fraud than the first range and the second range.

17. The method of claim 1, wherein at least one of the one or more insurance claim requests corresponds to an insurance claim for a particular accident, wherein determining at least one of the fraud potential indicators comprises applying one or more business rules to the at least one request corresponding to an insurance claim for a particular accident;

wherein at least of the one of the business rules applies a loss type multiplier based on at least one loss type associated with the request, wherein the value of the loss type multiplier depends on a tendency for fraud associated with a request type of the request.

18. The method of claim 1, wherein at least one of the one or more insurance claim requests corresponds to an insurance claim for a particular accident, wherein determining at least one of the fraud potential indicators comprises applying one or more business rules to the at least one request corresponding to an insurance claim for a particular accident;

wherein at least of the one of the business rules applies an injury type multiplier based on at least one injury type associated with the request, wherein the value of the injury type multiplier depends on a tendency for fraud associated with at least one injury type associated with the request.

19. The method of claim 1, wherein computing the one or more numerical values for the at least one fraud potential indicator using one or more formulas comprises:

multiplying an injury type multiplier by at least one other numerical value to produce the numerical value for the at least one fraud potential indicator, wherein the value of the injury type multiplier varies depending on the type of bodily injury alleged to have been sustained in an accident.

20. The method of claim 19, wherein, for the at least one fraud potential indicator, the injury type multiplier for at least one of the computed numerical values has a negative value, wherein a negative value of an injury type multiplier is contra-indicative of fraud.

21. The method of claim 1, wherein, for the at least one fraud potential indicator, the at least one other value for at least one of the computed numerical values comprises a number of matches in a database.

22. The method of claim 1, wherein the accident is a vehicle accident, wherein the numerical value of the loss type multiplier varies depending on the type of vehicle accident, wherein the type of vehicle accident comprises a failure to yield, hit and run, or a single vehicle collision.

23. A computer readable non-transitory storage medium comprising program instructions stored thereon, wherein the program instructions are executable to implement:

accessing, by a user system, an insurance request processing computer system;

transmitting one or more insurance claim requests relating to an accident to the insurance request processing computer system, wherein at least one of the insurance claim requests comprises one or more request data elements;

assessing, by the insurance request processing computer system, at least one fraud potential indicator for an insurance claim request relating to the accident, wherein the at least one fraud potential indicator comprises a numerical estimate of a probability of fraud in the insurance claim request, wherein the assessing of the at least one fraud potential indicator comprises;

comparing, by the insurance request processing computer system, at least one of the request data elements to one or more fraud models comprising at least one historical fraud pattern derived from insurance claims that have been proven fraudulent, wherein comparison of the at least one of the request data elements to one or more fraud models comprises searching for request patterns in the one or more request data elements that are similar to the at least one historical fraud pattern; and

an application of applying, by the insurance request processing computer system, one or more business rules to at least one of the request data elements, the application of the one or more business rules comprising;

computing one or more numerical values for the at least one fraud potential indicator using one or more formulas, wherein computing at least one of the numerical values for the at least one fraud potential indicator comprises;

multiplying a loss type multiplier by at least one other numerical value to produce the numerical value for the at least one fraud potential indicator, wherein the value of the loss type multiplier varies depending on the type of accident; and

automatically assigning the insurance claim request if one or more fraud potential indicators is within a fraud range.

24. An insurance processing system comprising:

a CPU;

a memory coupled to the CPU, wherein the memory comprises program instructions executable to implement;

accessing an insurance request processing computer system;

transmitting one or more insurance claim requests relating to an accident to the insurance request processing computer system, wherein at least one of the insurance claim requests comprises one or more request data elements;

assessing at least one fraud potential indicator for an insurance claim request relating to the accident, wherein the at least one fraud potential indicator comprises a numerical estimate of a probability of fraud in the insurance claim request, wherein the assessing of the at least one fraud potential indicator comprises;

comparing at least one of the request data elements to one or more fraud models comprising at least one historical fraud pattern derived from insurance claims that have been proven fraudulent, wherein comparison of the at least one of the request data elements to one or more fraud models comprises searching for request patterns in the one or more request data elements that are similar to the at least one historical fraud pattern; and

applying one or more business rules to at least one request data elements, the application of the one or more business rules comprising;

computing one or more numerical values for the at least one fraud potential indicator using one or more formulas, wherein computing at least one of the numerical values for the at least one fraud potential indicator comprises;

 

multiplying a loss type multiplier by at least one other numerical value to produce the numerical value for the at least one fraud potential indicator, wherein the value of the loss type multiplier varies depending on the type of accident; and

automatically assigning the insurance claim request if one or more fraud potential indicators is within a fraud range.