Systems, methods, and media for determining fraud patterns and creating fraud behavioral models

• US 8,793,131 B2
• Filed: 11/04/2011
• Issued: 07/29/2014
• 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: Guerra, Lisa, Gutierrez, Richard, Hartig, David, Rajakumar, Anthony, Vyas, Vipul
• Primary Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US13/290,011
• Publication Number:
  US 20120072453A1
• Time in Patent Office: 998 Days
• US Class Current: 704/246
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: H04L 9/32 including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2203/6027 Fraud preventions
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls

Abstract

Systems, methods, and media for analyzing fraud patterns and creating fraud behavioral models are provided herein. In some embodiments, methods for analyzing call data associated with fraudsters may include executing instructions stored in memory to compare the call data to a corpus of fraud data to determine one or more unique fraudsters associated with the call data, associate the call data with one or more unique fraudsters based upon the comparison, generate one or more voiceprints for each of the one or more identified unique fraudsters from the call data, and store the one or more voiceprints in a database.

Claims

1. A method for analyzing call data associated with fraudsters, the method comprising:

executing instructions stored in memory, the instruction to be executable by a processor, the instructions being configured to;

responsive to receiving call data associated with fraudsters, compare the call data to a corpus of fraud data to determine one or more unique fraudsters associated with the call data;

associate the call data with one or more unique fraudsters based upon the comparison;

generate one or more voiceprints for each of the one or more identified unique fraudsters from the call data;

store the one or more voiceprints for each of the one or more identified unique fraudsters from the call data in a database;

associate two or more voiceprints together that are determined to belong to the same unique fraudster into a group;

generate a master voiceprint for the group based upon the two or more voiceprints;

generate a fraud behavioral model for one or more voiceprints in a group, the fraud behavioral model including data that identifies behaviors of a unique fraudster; and

validate the association of the two or more voiceprints by comparing call data of the two or more voiceprints with the fraud behavioral model.

2. The method according to claim 1, further comprising:

compare the one or more voiceprints to one or more additional voiceprints stored in the database to generate a relative comparison score for the one or more voiceprints relative to each of the one or more additional voiceprints; and

group together each of the one or more additional voiceprints having a relative comparison score above a threshold amount.

3. The method according to claim 2, further comprising:

verify the group by manually listening to each voiceprint within the group; and

generate a master voiceprint for the group if the group is verified.

4. A method for identifying fraud patterns in call data, the method comprising:

executing instructions stored in memory, the executable instructions to be executed by a processor, for;

analyzing call data associated with fraudsters utilizing voice recognition techniques, the call data being received by a web server associated with one or more entities;

determining keywords included in the call data that are indicative of fraud;

identifying fraud patterns from the keywords;

generating a fraud analytics report based on the fraud patterns, the fraud analytics report comprising a set of visual graphs illustrating the fraud patterns, wherein a visual graph of the set of visual graphs comprises a first axis associated with the unique fraudsters and a second axis associated with a number of calls made; and

storing the fraud patterns in a database communicatively coupled with the web server.

5. The method according to claim 4, wherein keywords may include any of a credit card number, a social security numbers, a bank account number, a telephone number, a name, a location, a username, a password, personally identifiable information, and combinations thereof.

6. The method according to claim 4, wherein the fraud patterns comprise any of a frequency of fraud, a time and a date of fraud, a voice accent, a phone number called from, a phone number called to, a gender, a number of calls made, a number of enterprises being victimized, details of the enterprises being victimized, accomplice details, and combinations thereof.

7. The method according to claim 4, wherein a visual graph of the set of visual graphs comprises a first axis associated with a uniquely identified fraudster and a second axis associated with a number of accounts.

8. The method according to claim 4, wherein a visual graph of the set of visual graphs comprises a first axis associated with a number of unique fraudsters and a second axis associated with a number of accounts.

9. A system for identifying fraud patterns in call data, comprising:

a memory for storing executable instructions; and

a processor for executing the instructions, the executable instructions including;

an analytics engine that analyzes call data associated with fraudsters utilizing voice recognition techniques, the call data being received by a web server associated with one or more entities; and

determines keywords included in the call data that are indicative of fraud;

a fraud pattern identifying module that identifies fraud patterns from the keywords and stores the fraud patterns in a database communicatively coupled with the web server; and

a reports generator that generates a fraud analytics report based on the fraud patterns, the fraud analytics report comprising a set of visual graphs illustrating the fraud patterns, wherein a visual graph of the set of visual graphs comprises a first axis associated with a uniquely identified fraudster and a second axis associated with a number of accounts.

10. The system according to claim 9, wherein keywords may any of a credit card number, a social security numbers, a bank account number, a telephone number, a name, a location, a username, a password, personally identifiable information, and combinations thereof.

11. The system according to claim 9, wherein the fraud patterns comprise any of a frequency of fraud, a time and a date of fraud, a voice accent, a phone number called from, a phone number called to, a gender, a number of calls made, a number of enterprises being victimized, details of the enterprises being victimized, accomplice details, and combinations thereof.

12. The system according to claim 9, wherein a visual graph of the set of visual graphs comprises a first axis associated with the unique fraudsters and a second axis associated with a number of calls made.

13. The method according to claim 9, wherein a visual graph of the set of visual graphs comprises a first axis associated with a number of unique fraudsters and a second axis associated with a number of accounts.

14. A non-transitory computer readable storage media having a program embodied thereon, the program being executable by a processor to perform a method for analyzing fraud patterns in call data, the method comprising:

responsive to receiving call data associated with fraudsters, comparing the call data to a corpus of fraud data to determine one or more unique fraudsters associated with the call data;

associating the call data with one or more unique fraudsters based upon the comparison;

generating one or more voiceprints for each of the one or more identified unique fraudsters from the call data;

storing the one or more voiceprints in a database;

comparing the one or more voiceprints to one or more additional voiceprints stored in the database to generate a relative comparison score for the one or more voiceprints relative to each of the one or more additional voiceprints; and

grouping together each of the one or more additional voiceprints having a relative comparison score above a threshold amount; and

verifying the group by manually listening to each voiceprint within the group and generating a master voiceprint for the group if the group is verified.