Document fraud detection

• US 10,452,908 B1
• Filed: 12/23/2016
• Issued: 10/22/2019
• Est. Priority Date: 12/23/2016
• Status: Active Grant

• Current Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Original Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Inventors: Ramanathan, Ramanathan, Bejjanki, Ramakrishna, Ketharaju, Rameshchandra Bhaskar, Charugundla, Sumanth Kumar, Ammiraju, Prasanna Kumar
• Primary Examiner(s): Patel, Jayesh A
• Application Number:
  US15/389,630
• Time in Patent Office: 1,033 Days
• Field of Search: None
• CPC Class Codes: G06V 10/145 Illumination specially adapted for pattern recognition, e.g. using gratings
• CPC Class Codes: G06V 30/186 by deriving mathematical or geometrical properties from the whole image
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images
• CPC Class Codes: G06V 40/40 Spoof detection, e.g. liveness detection
• CPC Class Codes: G07D 7/00 Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
• CPC Class Codes: G07D 7/06 using wave or particle radiation
• CPC Class Codes: G07D 7/14 using chemical means
• CPC Class Codes: G07D 7/20 Testing patterns thereon G07D7/004, G07D7/005 take precedence

Abstract

Systems and methods provide for a document fraud detection system for identifying fraudulent documents. The document fraud detection system can include up to three steps of fraud detection, where if the document fails any of the three steps, the document can be flagged for further review. In another embodiment, the document fraud detection system can score each of the three tests, where the scores represent the likelihood that the document is fraudulent. If the combined score satisfies a predetermined criterion, the document can be flagged as potentially fraudulent. The three tests can include analyzing an scanned image of the document and comparing to other similar documents to determine if there have been any alterations. The second test can compare indents to previous documents, and the third test can analyze chemical and biometric factors that may indicate whether the document has been altered.

Claims

1. A system for identifying a fraudulent financial instrument, comprising:

a memory configured to store computer-executable instructions; and

a processor, communicatively coupled to the memory, configured to execute the computer-executable instructions to perform operations, the operations comprising;

scanning a financial instrument and matching a pattern of the financial instrument to a predetermined design, wherein if the pattern matches the predetermined design within a first threshold, the financial instrument passes a first verification check, wherein the scanning the financial instrument also determines a number of layers to the financial instrument, wherein a layer represents various times that the financial instrument has been altered by different people or objects;

upon a determination that there are multiple layers to the financial instrument, comparing transaction details on the financial instrument to a transaction detail pattern based on a previous transaction, wherein if the transaction details match the transaction detail pattern within a second threshold, the financial instrument passes a second verification check;

performing biometric and thermal scanning of the financial instrument and comparing scan results to a predetermined biometric and thermal pattern, wherein if the scan results match the predetermined biometric and thermal pattern within a third threshold, the financial instrument passes a third verification check;

flagging the financial instrument as potentially fraudulent in response to failing at least one of the first verification check, the second verification check, or the third verification check.

2. The system of claim 1, wherein the scanning is performed via at least one of an infrared scanner and an x-ray scanner.

3. The system of claim 1, wherein the operations further comprise:

skipping the comparing transaction details in response to determining that the financial instrument only comprises a single layer.

4. The system of claim 1, wherein the transaction detail pattern is based on a function of pattern of payments, available balance, check issuance dates, and payee information.

5. The system of claim 1, wherein the predetermined biometric and thermal pattern is based on a function of handwriting analysis based on the previous financial instrument, a heat map of hand contact with a medium of the financial instrument, or biometric information received from a chemical analysis of the financial instrument.

6. The system of claim 5, wherein the predetermined biometric and thermal pattern is based on a past sweat pattern of a previous financial instrument associated with the previous transaction, and the financial instrument fails the third verification check in response to sweat pattern of the financial instrument not matching the past sweat pattern.

7. The system of claim 1, wherein the operations further comprise:

assigning a score representing a likelihood of fraud for each of the first verification check, the second verification check, and the third verification check, and flagging the financial instrument as fraudulent in response to a combined score exceeding a predetermined value.

8. The system of claim 7, wherein the score for each of the first verification check, the second verification check, and the third verification check are weighted based on a predetermined weighting and the combined score is based on the weighted scores.

9. The system of claim 1, wherein operations associated with the second verification check comprise:

determining that a layer of the multiple layers is an indent pattern that does not match writing on the financial instrument; and

flagging the financial instrument in response to the indent pattern not matching writing on another financial instrument associated with the previous transaction.

10. The system of claim 1, wherein the operations further comprise:

determining an age of ink via the thermal scanning and matching the age of the ink to a date on the financial instrument.

11. A method for identifying a fraudulent financial instrument, comprising:

performing, by a device comprising a scanner, a first verification check comprising matching a scanned image of a financial instrument to a predetermined design within a first threshold;

performing, by the device, a second verification check comprising matching transaction details on the financial instrument to a transaction detail pattern based on a previous transaction to within a second threshold;

performing, by the device, biometric and thermal scanning of the financial instrument and matching scan results to a predetermined biometric and thermal pattern to within a third threshold; and

flagging, by the device, the financial instrument as potentially fraudulent in response to failing at least one of the first verification check, the second verification check, and the third verification check.

12. The method of claim 11, further comprising:

determining, by the device, number of layers to the financial instrument, and in response to there being a single layer, skipping the second verification check.

13. The method of claim 11, wherein the scanner comprises a thermal scanner or an x-ray scanner.

14. The method of claim 11, wherein the performing the second verification check further comprises:

determining that an indent pattern on the financial instrument does not match words on the financial instrument; and

flagging the financial instrument in response to the indent pattern not matching writing on another financial instrument associated with the previous transaction.

15. The method of claim 11, wherein the transaction detail pattern is based on a function of pattern of payments, available balance, check issuance dates, and payee information.

16. The method of claim 11, wherein the predetermined biometric and thermal pattern is based on a function of handwriting analysis based on a previous financial instrument associated with the previous transaction, a heat map of hand contact with a medium of the financial instrument, or biometric information received from a chemical analysis of the financial instrument.

17. The method of claim 11, further comprising:

assigning a score representing a likelihood of fraud for each of the first verification check, the second verification check, and the third verification check, and flagging the financial instrument as fraudulent in response to a combined score exceeding a predetermined value.

18. A non-transitory computer-readable medium, comprising instructions that when executed by a computer processor perform operations, comprising:

performing a first verification check comprising determining a first variance score of a scanned image of a financial instrument to a predetermined design;

performing a second verification check comprising determining a second variance score of transaction details on the financial instrument to a transaction detail pattern based on a previous transaction;

performing biometric and thermal scanning of the financial instrument and determining a third variance score of scan results to a predetermined biometric and thermal pattern; and

flagging the financial instrument for further review in response to a combined score of the first variance score, the second variance score, and the third variance score satisfying a predetermined score.

19. The non-transitory computer-readable medium of claim 18, wherein the operations further comprise:

determining, by the device, number of layers to the financial instrument, and in response to there being a single layer, skipping the second verification check.

20. The non-transitory computer readable medium of claim 18, wherein the operations further comprise:

determining that an indent pattern on the financial instrument does not match words on the financial instrument; and

flagging the financial instrument in response to the indent pattern not matching writing on another financial instrument associated with the previous transaction.