Fraud detection mechanism adapted for inconsistent data collection

• US 8,332,230 B2
• Filed: 09/15/2004
• Issued: 12/11/2012
• Est. Priority Date: 07/28/2004
• Status: Active Grant

• Current Assignee: Pitney Bowes Incorporated (Böwe Systec AG)
• Original Assignee: Pitney Bowes Incorporated (Böwe Systec AG)
• Inventors: Ryan, Frederick W. Jr.
• Primary Examiner(s): Jabr, Fadey
• Application Number:
  US10/941,539
• Publication Number:
  US 20060026102A1
• Time in Patent Office: 3,009 Days
• Field of Search: 705/57, 705 60- 62, 705400-411, 705/1.1, 705/330
• US Class Current: 705/1.1
• CPC Class Codes: G07B 17/00362 Calculation or computing within apparatus, e.g. calculation of postage value
• CPC Class Codes: G07B 17/00435 Details specific to central, non-customer apparatus, e.g. servers at post office or vendor
• CPC Class Codes: G07B 2017/00427 Special accounting procedures, e.g. storing special information
• CPC Class Codes: G07B 2017/00443 Verification of mailpieces, e.g. by checking databases

Abstract

Fraud detection mechanisms and methods that are adapted for inconsistent data collection are provided. Data is analyzed to determine normal operational variations from ideal system behavior. Profiles are developed for each individual sender, e.g., the number of multiple scans performed per confirmation number generated by each sender, and other parameters, such as delivery areas, e.g., the number of multiple scans performed per specific geographic area. If the sender'"'"'s profile differs significantly from the normal operational variations, there is an indication of potential fraudulent activity and an investigation can be initiated. By analyzing a combination of sender and delivery scan data with system wide scan data, the effect of inconsistent data is minimized to significantly reduce the number of erroneous indications of fraudulent activity while still providing a high level of fraud detection.

Claims

1. In a verification system including a processing device, the verification system having items intended for a single use, in which usage of an item is confirmed by scanning an identification number associated with the item, and wherein scanning activity is inconsistent, a method for identifying a suspect for fraudulent use of the identification numbers comprising:

creating, by the processing device, a profile of scanning activity for a plurality of items that meet a first parameter, the profile including a percentage of items that meet the first parameter that have been scanned more than once;

creating, by the processing device, a profile of scanning activity for a plurality of items used by a specified user, the profile including a total number of scans for items used by the specified user that meet the first parameter and a percentage of items used by the specified user that meet the first parameter that have been scanned more than once;

analyzing, by the processing device, the profile of scanning activity for the plurality of items used by the specified user to determine that the total number of scans for items used by the specified user that meet the first parameter exceeds a predetermined minimum number and that the percentage of items used by the specified user that meet the first parameter that have been scanned more than once is greater than a first threshold value, the first threshold value being based on the percentage of items that meet the first parameter that have been scanned more than once from the profile of scanning activity for the plurality of items that meet the first parameter; and

identifying, by the processing device, the specified user as a suspect for fraudulent use of the identification numbers.

2. The method of claim 1, wherein before identifying the specified user as a suspect for fraudulent use of the identification numbers the method further comprises:

determining if an extended fraud detection check is required;

if it is determined that an extended fraud detection is required, performing the extended fraud detection; and

if it is determined that an extended fraud detection check is not required, then identifying the specified user as a suspect for fraudulent use of the identification numbers.

3. The method of claim 2, wherein performing the extended fraud detection check further comprises:

creating, by the processing device, a profile of scanning activity for a plurality of items used by the specified user that meet a second parameter, the second parameter being a subset of the first parameter, the profile of scanning activity for the plurality of items used by the specified user that meet the second parameter including a total number of scans for items used by the specified user that meet the second parameter and a percentage of items used by the specified user that meet the second parameter which have been scanned more than once;

analyzing, by the processing device, the profile of scanning activity for the plurality of items used by the specified user that meet the second parameter to determine that the total number of scans for items used by the specified user that meet the second parameter is greater than a predetermined minimum number for the second parameter and that the percentage of items used by the specified user that meet the second parameter that have been scanned more than once is greater than a second threshold value; and

identifying the specified user as a suspect for fraudulent use of the identification numbers.

4. The method of claim 3, wherein the first parameter is use of the item in a first geographic region, and the second parameter is use of the item in a second geographic region, the second geographic region being a subset of the first geographic region.

5. The method of claim 1, wherein the profile of scanning activity for a plurality of items that meet the first parameter further includes a total number of scans performed.

6. The method of claim 5, wherein the profile of scanning activity for a plurality of items that meet the first parameter further includes a percentage of identification numbers scanned more than once within a predetermined period of time and a percentage of identification numbers scanned more than once on different days.

7. The method of claim 1, wherein the items are indicia that evidence payment of postage for mail pieces.

8. The method of claim 7, wherein the identification number is a delivery confirmation number.

9. The method of claim 7, wherein the first parameter is a class of service for the mail pieces.

10. The method of claim 1, wherein the item are coupons.

11. The method of claim 1, wherein the first parameter is use of an item in a first geographic region.

12. A system for identifying a suspect for fraudulent use of identification numbers associated with items intended for a single use, wherein usage of an item is confirmed by scanning the identification number associated with the item, and wherein scanning activity is inconsistent, the system comprising:

a database for storing data associated with scanning the identification numbers;

a processing device coupled to the database, the processing device being configured to create a profile, from the data stored in the database, of scanning activity for a plurality of items that meet a first parameter, the profile including a percentage of items that meet the first parameter that have been scanned more than once;

create, from the data stored in the database, a profile of scanning activity for a plurality of items used by a specified user, the profile including a total number of scans for items used by the specified user that meet the first parameter and a percentage of items used by the specified user that meet the first parameter that have been scanned more than once;

analyze the profile of scanning activity for the plurality of items used by the specified user to determine that the total number of scans for items used by the specified user that meet the first parameter exceeds a predetermined minimum number and that the percentage of items used by the specified user that meet the first parameter that have been scanned more than once is greater than a first threshold value, the first threshold value being based on the percentage of items that meet the first parameter that have been scanned more than once from the profile of scanning activity for the plurality of items that meet the first parameter; and

identify the specified user as a suspect for fraudulent use of the identification numbers based on the percentage of items used by the specified user that meet the first parameter that have been scanned more than once from the profile of scanning activity for the plurality of items used by a specified user being greater than the first threshold value.

13. The system of claim 12, wherein the processing device is further configured to determine

if an extended fraud detection check is required,

wherein before identifying the specified user as a suspect for fraudulent use of the identification numbers, it is determined if an extended fraud detection check is required, and if it is determined that an extended fraud detection check is required, the extended fraud detection check is performed, and if it is determined that an extended fraud detection check is not required, then the specified user is identified as a suspect for fraudulent use of the identification numbers.

14. The system of claim 13, wherein the processing device is further configured to

create, from data stored in the database, a profile of scanning activity for a plurality of items used by the specified user that meet a second parameter, the second parameter being a subset of the first parameter, the profile of scanning activity for the plurality of items used by the specified user that meet the second parameter including a total number of scans for items used by the specified user that meet the second parameter and a percentage of items used by the specified user that meet the second parameter that have been scanned more than once;

analyze the profiled of scanning activity for the plurality of items used by the specified user that meet the second parameter to determine that the total number of scans for

items used by the specified user that meet the second parameter is greater than a predetermined minimum number for the second parameter and that the percentage of items used by the specified user that meet the second parameter that have been scanned more than once is greater than a second threshold value, and to identify

the specified user as a suspect for fraudulent use of the identification numbers based on the percentage of items used by the specified user that meet the second parameter that have been scanned more than once being greater than the second threshold value.

15. The system of claim 14, wherein the first parameter is use of an item in a first geographic region, and the second parameter is use of an item in a second geographic region, the second geographic region being a subset of the first geographic region.

16. The system of claim 12, wherein the profile of scanning activity for a plurality of items used that meet the first parameter further includes a total number of scans performed.

17. The system of claim 16, wherein the profile of scanning activity for a plurality of for items used that meet the first parameter further includes a percentage of identification numbers scanned more than once within a predetermined period of time and a percentage of identification numbers scanned more than once on different days.

18. The system of claim 12, wherein the items are indicia that evidence payment of postage for mail pieces.

19. The system of claim 18, wherein the identification number is a delivery confirmation number.

20. The system of claim 18, wherein the first parameter is a class of service for the mail pieces.

21. The system of claim 12, wherein the item are coupons.

22. The system of claim 12, wherein the fist parameter is use of an item in a first geographic region.