Comprehensive Identity Protection System

• US 20070124256A1
• Filed: 06/02/2006
• Published: 05/31/2007
• Est. Priority Date: 06/02/2005
• Status: Active Grant

• Current Assignee: Fair Isaac Corporation
• Original Assignee: Fair Isaac Corporation
• Inventors: Mayer, Uwe, Crooks, Theodore, Lazarus, Michael
• Granted Patent: US 7,849,029 B2
• Time in Patent Office: Days
• US Class Current: 705/80
• 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 20/4016 involving fraud or risk level assessment in transaction processing
• CPC Class Codes: G06Q 20/403 Solvency checks
• CPC Class Codes: G06Q 50/18 Legal services
• CPC Class Codes: G06Q 50/188 Electronic negotiation

Abstract

A system and method for protecting identity fraud are disclosed. A system includes a detection subsystem to identify applications and/or accounts at risk of identity fraud, and a disposition subsystem to process data provided by the detection system and to determine whether identity fraud exists in the applications and/or accounts. According to an implementation, one or more neural network models are defined, each neural network model being configured to handle a class of cases related to the subject and a specific data configuration describing a case of the class. The one or more neural network models are run to generate data requests about the subject'"'"'s identity, and the data requests are passed to a detection system that monitor transactions associated with the subject. Additional data associated with the transactions is requested until a threshold certainty is achieved or until available data or models are exhausted.

Claims

1. A method of protecting a subject'"'"'s identity, the method comprising:

defining one or more neural network models, each neural network model being configured to handle a class of cases related to the subject and a specific data configuration describing a case of the class;

running the one or more neural network models to generate data requests about the subject'"'"'s identity; and

passing the data requests to a detection system that monitor transactions associated with the subject.

2. A method in accordance with claim 1, further comprising monitoring the transactions associated with the subject.

3. A method in accordance with claim 2, further comprising gathering data in response to the data requests.

4. A method in accordance with claim 3, further comprising determining whether a particular transaction associated with the subject includes fraudulent activity.

5. A method in accordance with claim 4, further comprising running the one or more neural network models until the determining whether the particular transaction associated with the subject includes fraudulent activity achieves a threshold level of certainty.

6. A method in accordance with claim 1, wherein the data requests are passed to a data manager module in the detection system, and wherein the detection system further includes one or more monitors, each monitor being associated with an installed system on which the transactions associated with the subject occur.

7. A method in accordance with claim 3, wherein the gathered data in response to the data requests is processed by a disposition system.

8. A method in accordance with claim 7, further comprising storing processed data in an identity clearinghouse.

9. A computer-implemented method to identify fraud in transactions on one or more systems used by a subject, the method comprising:

running one or more neural network models from a set of neural network models to request data associated with the transactions; and

requesting additional data associated with the transactions until a threshold certainty is achieved or until available data or models are exhausted.

10. A method in accordance with claim 9, wherein requesting additional data includes running another neural network model from the set of neural network models.

13. A method in accordance with claim 9, wherein each neural network model is run by a monitor that monitors transactions on one system of the one or more systems.

14. A method in accordance with claim 9, further comprising generating data requests to the one or more systems with the one or more neural network models.

15. A method in accordance with claim 14, further comprising processing data based on the data requests to determine whether the transactions include fraud.

11. A method in accordance with 9, wherein the transactions include telecommunications.

12. A method in accordance with claim 11, wherein the transactions include banking transactions.

16. An identity protection system comprising:

a detection subsystem to identify applications and/or accounts at risk of identity fraud; and

a disposition subsystem to process data provided by the detection system and to determine whether identity fraud exists in the applications and/or accounts.

17. A system in accordance with claim 16, wherein the detection subsystem includes one or more monitors, each monitor associated with an application or an account.

18. A system in accordance with claim 17, wherein each monitor includes one or more neural network models.

19. A system in accordance with claim 18, wherein the detection subsystem further includes a data manager to manage the monitors and to execute the one or more neural network models.

20. A system in accordance with claim 19, wherein the disposition subsystem includes a case manager that receives data from the one or more monitors, processes the data, and determines whether identify fraud exists in the applications and/or accounts.