Method and system for generating a fraud risk score using telephony channel based audio and non-audio data

• US 8,930,261 B2
• Filed: 08/13/2010
• Issued: 01/06/2015
• Est. Priority Date: 04/21/2005
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Inventors: Hartig, David, Rajakumar, Anthony, Guerra, Lisa Marie, Gutierrez, Richard
• Primary Examiner(s): Colbert, Ella
• Assistant Examiner(s): CRANFORD, MICHAEL D
• Application Number:
  US12/856,118
• Publication Number:
  US 20100303211A1
• Time in Patent Office: 1,607 Days
• Field of Search: 705/38
• US Class Current: 705/38
• CPC Class Codes: G06Q 20/24 Credit schemes, i.e. "pay after"
• CPC Class Codes: G06Q 20/305 using wired telephone networks
• CPC Class Codes: G06Q 20/40 Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
• CPC Class Codes: G06Q 20/4014 Identity check for transactions
• CPC Class Codes: G06Q 20/40145 Biometric identity checks
• CPC Class Codes: G06Q 20/4016 involving fraud or risk level assessment in transaction processing
• CPC Class Codes: H04M 15/00 Arrangements for metering, time-control or time indication ; Metering, charging or billing arrangements for voice wireline or wireless communications, e.g. VoIP
• CPC Class Codes: H04M 15/47 Fraud detection or prevention means
• CPC Class Codes: H04M 2215/0148 Fraud detection or prevention means

Abstract

Disclosed is a method for generating a fraud risk score representing a fraud risk associated with an individual, the method comprising: a) determining a telephony channel risk score from at least one of audio channel data and non-audio channel data of the individual; and b) generating the fraud risk score based on at least one of the telephony channel risk score, the audio channel data, and the non-audio channel data.

Claims

1. A method for generating fraud risk scores representing fraud risks associated with an individual, the method comprising:

determining calculating an audio channel fraud risk score from audio channel data of the individual comprising at least one of an emotion or stress extracted from an audio signal representing a voice sample of the individual when the individual responded to specific questions designed to trigger stress in fraudsters but not in legitimate callers, the voice sample of the individual, and keywords extracted from the audio signal of the voice sample, the audio channel fraud risk score calculated by a computer processor coupled to a memory and including a telephony risk score calculator;

determining calculating a non-audio channel fraud risk score from non-audio channel data of the individual, the non-audio channel data comprising at least one of a type of telephony system used by the individual and a geographic location of the individual, the non-audio channel fraud risk score calculated by the telephony risk score calculator; and

generating an aggregate fraud risk score based on the audio channel fraud risk score and the non-audio channel fraud risk score, the aggregate fraud risk score generated by an aggregate risk score generator included in the computer processor coupled to a memory.

2. The method of claim 1, wherein the telephony system comprises one of a Public Switched Telephone Network, a mobile phone, and Voice Over Internet Protocol network.

3. The method of claim 1, wherein the non-audio channel data comprises at least one of a phone number called from, a phone number called to, a time duration for which the individual has had the phone number, a call frequency to/from the phone number called from, the area code of the phone number called from, a number of routing hops needed to complete the call, geography associated with an area code of the phone number called from, geographical location of the individual, whether the individual called from an expected phone number or a non-published number, whether the phone number is being call-forwarded and when that call forward was initiated, an identity data, transaction data, and Short Message Service channel data.

4. The method of claim 3, wherein the identity data comprises at least one of a name of the individual, a Social Security Number of the individual, an address of the individual, a phone number from which the individual called, and information related to background of the individual.

5. The method of claim 4, wherein the information related to the background of the individual includes at least one of previous addresses lived at, persons that the individual shared a residence with, mother'"'"'s maiden name, and a color of a first car.

6. The method of claim 1, wherein the audio channel data includes a voice sample of the individual and one or more keywords used by the individual, and the non-audio channel data includes order data associated with an order placed by the individual.

7. A risk score calculator for generating a fraud risk score representing a fraud risk associated with an individual, the calculator comprising:

a telephony risk score calculator programmed to determine at least one audio channel fraud risk score from audio channel data associated with the individual, the audio channel data comprising at least one of an emotion or stress extracted from an audio signal representing a voice sample of the individual when the individual responded to specific questions designed to trigger stress in fraudsters but not in legitimate callers, the voice sample of the individual, and keywords extracted from the audio signal of the voice sample, the telephony fraud risk score calculator further programmed to determine at least one non-audio channel fraud risk score from non-audio channel data associated with the individual, the non-audio channel data comprising at least one of a type of telephony system used by the individual and a geographic location of the individual; and

an aggregate risk score generator programmed to generate the fraud risk score based on an aggregate of at least audio channel fraud risk score and non-audio channel fraud risk score.

8. The risk score calculator of claim 7, wherein the telephony system comprises one of a Public Switched Telephone Network, a mobile phone, and Voice Over Internet Protocol network.

9. The risk score calculator of claim 7, wherein the non-audio channel data comprises at least one of a phone number called from, a phone number called to, a time duration for which the individual has had the phone number, a call frequency to /from the phone number called from, the area code of the phone number called from, a number of routing hops needed to complete the call, geography associated with an area code of the phone number called from, geographical location of the individual, whether the individual called from an expected phone number or a non-published number, whether the phone number is being call-forwarded and when that call-forward was initiated, an identity data, transaction data, and Short Message Service channel data.

10. The risk score calculator of claim 9, wherein the identity data comprises at least one of a name of the individual, a Social Security Number of the individual, an address of the individual, a phone number from which the individual called, and information related to background of the individual.

11. The risk score calculator of claim 10, wherein the information related to the background of the individual includes at least one of previous addresses lived at, persons that the individual shared a residence with, mother'"'"'s maiden name, and a color of a first car.

12. The risk score calculator of claim 7, wherein the at least one audio channel fraud risk score includes a voice match score based on a match between a voice print of a known fraudster and the individual.

13. A tangible computer readable medium containing a computer program product for generating a fraud risk score representing a fraud risk associated with an individual, the computer program product comprising:

program code for calculating an audio channel fraud risk score from audio channel data comprising at least one of an emotion or stress extracted from an audio signal representing a voice sample of the individual when the individual responded to specific questions designed to trigger stress in fraudsters but not in legitimate callers, the voice sample of the individual, and keywords extracted from the audio signal of the voice sample;

program code for calculating a non-audio channel fraud risk score from non-audio channel data of the individual, the non-audio channel data comprising at least one of a type of telephony system used by the individual and a geographic location of the individual; and

program code for generating the fraud risk score based on the audio channel fraud risk score and the non-audio channel fraud risk score.

14. The computer program product of claim 13, wherein the telephony system comprises one of a Public Switched Telephone Network, a mobile phone, and Voice Over Internet Protocol network.

15. The computer program product of claim 13, wherein the non-audio channel data comprises at least one of a phone number called from, a phone number called to, a time duration for which the individual has had the phone number, a call frequency to /from the phone number called from, the area code of the phone number called from, a number of routing hops needed to complete the call, geography associated with an area code of the phone number called from, geographical location of the individual, whether the individual called from an expected phone number or a non-published number, whether the phone number is being call-forwarded and when that call-forward was initiated, an identity data, transaction data, and Short Message Service channel data.

16. The computer program product of claim 15, wherein the identity data comprises at least one of a name of the individual, a Social Security Number of the individual, an address of the individual, a phone number from which the individual called, and information related to background of the individual.

17. The computer program product of claim 16, wherein the information related to the background of the individual includes at least one of previous addresses lived at, persons that the individual shared a residence with, mother'"'"'s maiden name, and a color of a first car.