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

• US 20050108063A1
• Filed: 11/05/2003
• Published: 05/19/2005
• Est. Priority Date: 11/05/2003
• Status: Abandoned Application

• Current Assignee: Computer Sciences Corporation (DXC Technology Company)
• Original Assignee: Computer Sciences Corporation (DXC Technology Company)
• Inventors: Thabani Mtshali, Progress Qhaqhi, Rogers, James Lewis, Madill, Robert P. Jr., Barger, Thomas Glenn
• Application Number:
  US10/702,088
• Publication Number:
  US 20050108063A1
• Time in Patent Office: Days
• 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, comprising:

providing at least one request data element for at least one request to a computer system;

assessing at least one fraud potential indicator for the at least one request based on at least two of;

a) at least one comparison of the at least one request data element to a datum in a database;

b) at least one comparison of the at least one request data element to at least one fraud model; and

c) at least one business rule applied to the at least one request data element;

wherein the at least one fraud potential indicator comprises an estimate of a probability of fraud in the at least one request.

2. The method of claim 1, wherein at least one request comprises at least one of:

a check;

an insurance claim; and

a loan.

3. The method of claim 1, further comprising assigning a total fraud potential indicator from at least two fraud potential indicators.

4. The method of claim 2, wherein the total fraud potential indicator is assigned by adding together the at least two fraud potential indicators.

5. The method of claim 2, wherein the total fraud potential indicator is assigned by averaging the at least two fraud potential indicators.

6. The method of claim 1, wherein at least one request data element comprises at least one of:

a claimant'"'"'s name;

a witness'"'"'s name;

an insured'"'"'s name;

a medical provider'"'"'s name;

an involved business'"'"'s name;

an involved business'"'"'s address;

a date of the at least one request;

a date of loss;

identification of an involved vehicle;

an inception date of a policy;

an expiration date of a policy;

an address of a party related to the at least one request;

a detail of the loss or an accident leading to the loss;

a detail of an accident;

a type of accident;

a number of parties involved;

a type or degree of property damage;

a type or degree of injuries;

a trajectory of vehicles in a vehicle accident; and

a location of an accident.

7. The method of claim 1, wherein the at least one request data element comprises at least one of:

information on a drawer;

a payee;

a date;

an account number;

a routing number; and

involved banks.

8. The method of claim 1, wherein the at least one request data element comprises at least one of:

information about a loan applicant;

a loan applicant'"'"'s credit history;

another debt of the loan applicant;

an income level of the loan applicant;

a criminal history of the loan applicant;

a social security number;

an address;

other obligations;

information on an item to be purchased with loan proceeds; and

information about another party involved in the loan.

9. The method of claim 1, wherein the at least one comparison of at least one request data element to at least one fraud model comprises determining if at least one request data element approximately matches at least one fraud model.

10. The method of claim 1, wherein the at least one comparison of at least one request data element to at least one fraud model comprises assigning a fraud potential indicator based on the nearness of an approximate match of a fraud model to at least one request data element.

11. The method of claim 1, wherein assessing at least one fraud potential indicator comprises determining if at least one request data element approximately matches at least one fraud model, and assessing at least one fraud potential indicator based on which request data element is approximately matched.

12. The method of claim 1, wherein assessing at least one fraud potential indicator comprises determining if at least one request data element approximately matches at least a portion of a data element in a database.

13. The method of claim 1, further comprising referring the at least one request for review if at least one fraud potential indicator exceeds a threshold value.

14. The method of claim 13, wherein the threshold value is adjusted to control the number of requests with at least one fraud potential indicator exceeding the threshold value.

15. The method of claim 1, further comprising:

assigning a total fraud potential indicator based on at least one fraud potential indicator; and

referring at least one request for review if the total fraud potential indicator exceeds a threshold value.

16. The method of claim 1, wherein at least one fraud model is based on at least one historical fraud pattern.

17. The method of claim 1, wherein at least one fraud potential indicator comprises at least one of:

a numerical indicator;

a ranking; and

a pass/fail indicator.

18. The method of claim 1, wherein assessing the at least one fraud potential indicator includes determining an absence of fraud in a request.

19. The method of claim 1, further comprising assessing the probability of fraud in at least two requests, wherein the at least two requests are ranked in order of potential for fraud in each request.

20. The method of claim 1, wherein the at least one comparison of at least one request data element to a datum in a database comprises comparing at least one request data element to a watch list database, wherein the watch list database comprises at least one specified data element specified by an entity.

21. The method of claim 20, wherein the entity is notified if at least one request data element matches at least one specified element in the watch list.

22. The method of claim 1, wherein at least one fraud potential indicator is assessed for the at least one request using a predetermined formula.

23. The method of claim 22, wherein at least one fraud potential indicator is assessed using at least one comparison of at least one request data element to a datum in a database, wherein at least one fraud potential indicator is set approximately equal to a multiplier value multiplied by a loss type value multiplied by a number of matches between the at least one request data element to the datum found in a database searched.

24. The method of claim 22, wherein the multiplier value equals a ranking multiplied by a point weight multiplied by an adjustment number.

25. The method of claim 1, further comprising:

reassessing the at least one request data element for the at least one request; and

updating the at least one fraud potential indicator for the at least one request based on the reassessment.

26. The method of claim 1, wherein the database comprises at least one of:

an insurance industry database;

a commercial mailbox database;

a company historical request database;

a special investigation unit database;

a sanctioned medical providers database; and

a custom watch list database.

27. The method of claim 1, wherein the at least one fraud model comprises a suspicious relationship between parties involved in an accident.

28. The method of claim 1, wherein at least one business rule is used to assess a probability of fraud based on the details of an accident.

29. The method of claim 1, wherein at least one business rule compares a date of report of a loss and a date of the loss.

30. The method of claim 1, wherein at least one business rule compares a date of a reported loss and a date of inception of an insurance policy.

31. The method of claim 1, wherein at least one business rule compares a date of a reported loss and a date of expiration of an insurance policy.

32. The method of claim 1, wherein at least one business rule assesses a probability of fraud in the at least one request based on an injury type.

33. The method of claim 1, wherein at least one business rule assesses a probability of fraud in the at least one request based on a loss type.

34. The method of claim 1, wherein at least one business rule assesses a probability of fraud in the at least one request based on an existence of a police report.

35. The method of claim 1, wherein at least one business rule assesses a probability of fraud in the at least one request based on who reported the at least one request.

36. The method of claim 1, wherein at least one business rule assesses a probability of fraud in the at least one request based on the number of vehicles involved.

37. The method of claim 1, wherein at least one business rule assesses a probability of fraud in the at least one request based on time difference between the date of a check and the date the check is cashed.

38. The method of claim 1, wherein at least one business rule assesses a probability of fraud in the at least one request based a comparison of a loan applicant'"'"'s income to the loan applicant'"'"'s assets.

39. The method of claim 1, wherein assessing at least one fraud potential indicator for at least one insurance claim is based on an identity verification engine to verify the identification of at least one data request element.

40. The method of claim 39, wherein at least one data request element verified includes an insured, a claimant, a doctor, a lawyer, or an involved business.

41. The method of claim 39, wherein at least one of a public record and a bill is used to verify the identification of at least one request data element.

42. A computer system, comprising:

a CPU; and

a memory coupled to the CPU, wherein the memory is configured to store at least one computer program executable by the CPU, and wherein at least one computer program is executable to;

provide at least one request data element for at least one request to the computer system;

assess at least one fraud potential indicator for the at least one request based on at least two of;

a) at least one comparison of the at least one request data element to data in a database;

b) at least one comparison of the at least one request data element to at least one fraud model; and

c) at least one business rule applied to the at least one request data element;

wherein the at least one fraud potential indicator comprises an estimate of a probability of fraud in a request.

43. The system of claim 42, wherein the at least one request comprises at least one of:

a check;

an insurance claim; and

a loan.

44. The system of claim 42, wherein the computer program is further executable to assess a total fraud potential indicator of the at least one request from at least two fraud potential indicators.

45. The system of claim 42, wherein at least one comparison of the at least one request data element to the at least one fraud model comprises determining if the at least one request data element approximately matches the at least one fraud model.

46. The system of claim 42, wherein assessing at least one second fraud potential indicator comprises determining if the at least one request data element approximately matches at least a portion of a data element in a database.

47. The system of claim 42, wherein the computer program is further executable to refer the at least one request for review if at least one fraud potential indicator exceeds a threshold value.

48. A carrier medium comprising program instructions, wherein the program instructions are computer-executable to implement a method comprising:

providing at least one request data element for at least one request to a computer system;

assessing at least one fraud potential indicator for the at least one request based on at least two of;

a) at least one comparison of the at least one request data element to data in a database;

b) at least one comparison of the at least one request data element to at least one fraud model; and

c) at least one business rule applied to the at least one request data element;

wherein the at least one fraud potential indicator comprises an estimate of a probability of fraud in the at least one request.

49. The carrier medium of claim 48, wherein the at least one request comprises at least one of:

a check;

an insurance claim; and

a loan.

50. The carrier medium of claim 48, further comprising assessing a total fraud potential indicator of at least one request from at least two fraud potential indicators.

51. The carrier medium of claim 48, wherein at least one comparison of the at least one request data element to the at least one fraud model comprises determining if the at least one request data element approximately matches the at least one fraud model.

52. The carrier medium of claim 48, wherein assessing at least one second fraud potential indicator comprises determining if the at least one request data element approximately matches at least a portion of a data element in a database.

53. The carrier medium of claim 48, further comprising referring the at least one request for further review if at least one fraud potential indicator exceeds a threshold value.

54. A method, comprising:

assessing at least one fraud potential indicator for a plurality of insurance claims using at least one fraud potential detection technique; and

defining a minimum referral fraud potential indicator such that a desired quantity of requests are referred.

55. The method of claim 54, further comprising modifying a minimum referral fraud potential indicator for at least two fraud potential detection techniques using at least two fraud potential indicators from at least one fraud potential detection technique to obtain a selected quantity of referrals for further review.

56. The method of claim 54, wherein the minimum referral fraud potential indicator comprises a fraud potential indicator that results in a referral of at least one request for further review.

57. The method of claim 54, wherein at least one fraud potential detection technique comprises predictive modeling.

58. The method of claim 54, wherein at least one fraud potential detection technique comprises predictive modeling, and wherein assessing a probability of fraud using predictive modeling comprises assessing at least one fraud potential indicator based on at least one comparison of at least one request data element to at least one fraud model.

59. The method of claim 54, wherein at least one fraud potential detection technique comprises identity searching.

60. The method of claim 54, wherein at least one fraud potential detection technique comprises identity searching of insurance data, and wherein assessing the probability of fraud using identity search of insurance data comprises assessing at least one fraud potential indicator based on at least one comparison of at least one request data element to additional insurance data.

61. The method of claim 54, wherein at least one fraud potential detection technique comprises assessing request data for fraud from at least one business rule.

62. A system configured to estimate liability, comprising:

a CPU; and

a memory coupled to the CPU, wherein the memory is configured to store at least one computer program executable by the CPU, and wherein at least one computer program is executable to;

assess fraud potential indicators for a plurality of requests using at least one fraud potential detection technique; and

establish a minimum referral fraud potential indicator such that a desired quantity of requests are referred.

63. The system of claim 62, wherein the computer program is further executable to modify a minimum referral fraud potential indicator for at least two fraud potential detection techniques using at least two fraud potential indicators from at least one fraud potential detection technique to obtain a selected quantity of referral of requests for further review.

64. A carrier medium comprising program instructions, wherein the program instructions are computer-executable to implement a method comprising:

assessing a fraud potential indicator for a plurality of requests using at least one fraud potential detection technique; and

establishing a minimum referral fraud potential indicator such that a desired quantity of requests are referred.

65. The carrier medium of claim 64, further comprising modifying a minimum referral fraud potential indicator for at least two fraud potential detection techniques using at least two fraud potential indicators from at least one fraud potential detection technique to obtain a selected quantity of referral of requests for further review.

66-157. -157. (canceled)