DETECTING FIRST PARTY FRAUD ABUSE

• US 20090222308A1
• Filed: 03/03/2009
• Published: 09/03/2009
• Est. Priority Date: 03/03/2008
• Status: Abandoned Application

• Current Assignee: Fair Isaac Corporation
• Original Assignee: Fair Isaac Corporation
• Inventors: Derderian, Maria Edna Perez, Dempsey, Derek Malcolm, Zoldi, Scott M., Spoelstra, Jacob
• Application Number:
  US12/397,186
• Publication Number:
  US 20090222308A1
• Time in Patent Office: Days
• US Class Current: 705/7
• CPC Class Codes: G06Q 20/04 Payment circuits
• CPC Class Codes: G06Q 20/24 Credit schemes, i.e. "pay after"
• CPC Class Codes: G06Q 20/4016 involving fraud or risk level assessment in transaction processing
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 40/12 Accounting

Abstract

A computerized method includes analyzing data associated with a credit line during an origination stage for predictive variables for use in a model for first party fraud, and flagging an account during the origination stage when at least one or more predictive origination stage variables cause a model score to exceed a pre-defined fraud likelihood threshold. The computerized method also includes analyzing data associated with one or more previously flagged, post-booked stage credit lines for data elements or transactions to be used as variables in a model to predictive of first party fraud at the customer-level or in one or more of the post-booked stage credit lines.

Claims

1. A computerized method comprising:

analyzing data associated with a credit line during an origination stage for predictive variables for use in a model for first party fraud;

flagging an account during the origination stage when at least one or more predictive origination stage variables of first party cause a fraud score to exceed a pre-described fraud likelihood threshold;

analyzing data associated with one or more previously flagged, post-booked stage credit lines for elements to be used in a model to predict first party fraud in one or more of the post-booked stage credit lines.

2. The computerized method of claim 1 wherein the elements associated with analyzing data associated with one or more previously flagged, post-booked stage credit lines includes data;

3. The computerized method of claim 1 wherein analyzing data associated with a credit line during a pre-booked portion of the origination stage includes profiling of at least one entity associated with the originations process.

4. The computerized method of claim 1 wherein the elements associated with analyzing data associated with one or more previously flagged, post-booked stage credit lines includes computed variables.

5. The computerized method of claim 1 wherein analyzing data associated with the credit line during the origination stage for predictive variables includes analyzing the information provided by an entity applying for the credit line for false information.

6. The computerized method of claim 1 wherein analyzing data associated with a credit line during the post-booked stage includes analyzing the transactions during a selected, initial time period after approving a credit line.

7. The computerized method of claim 6 wherein analyzing the transactions during a selected, initial time period after approving the credit line includes analyzing the velocity of the transactions.

8. The computerized method of claim 6 wherein analyzing the transactions during a selected, initial time period after approving the credit line includes analyzing the size of the transactions.

9. The computerized method of claim 6 wherein analyzing the transactions during a selected, initial time period after approving the credit line includes analyzing the type of payment for the transactions.

10. The computerized method of claim 6 wherein analyzing the transactions during a selected, initial time period after approving the credit line includes analyzing the type of customer contacts associated with the credit line.

11. The computerized method of claim 6 wherein analyzing the transactions during a selected, initial time period after approving the credit line includes analyzing the type requests for additional credit.

12. The computerized method of claim 6 wherein analyzing the transactions during a selected, initial time period after approving the credit line includes analyzing customer information and address changes.

13. The computerized method of claim 11 wherein a payment on the account has been received.

14. The computerized method of claim 11 wherein a payment on the account has been received, and the payment has not yet cleared.

15. The computerized method of claim 1 wherein analyzing data associated with a credit line during the post-booked stage includes analyzing the transactions associated with a customer and one or more credit lines.

16. The computerized method of claim 1 wherein analyzing data associated with a credit line during the post-booked stage includes creation of transaction profile variables associated with the account and customer profiles.

17. The computerized method of claim 1 further comprising attempting to contact the entity associated with a flagged account.

18. The computerized method of claim 1 further compromising merging a first party fraud score associated with the application, origination stage with transaction data from the post-book stage to produce a second first party fraud score associated with the application and the post-book stage.

19. The computerized method of claim 1 wherein analyzing data associated with one or more credit lines that have previously been flagged includes searching for a condition where there is a request for an increase in a credit limit associated with the credit line.

20. A computer system comprising:

a first data analysis component for analyzing data associated with a credit line during an origination stage for predictive variables for use in a model for first party fraud;

an origination account scoring component that flags an account during the origination stage when at least one or more predictive origination stage variables of first party may cause a fraud score to exceed a pre-described fraud likelihood threshold;

a second data analysis component for analyzing data associated with one or more previously flagged, post-booked stage credit lines for transaction based profile variables to be used as variables in a model to predict first party fraud in one or more of the post-booked stage credit lines.

21. The computer system of claim 20 wherein the second data analysis component analyzes the transactions during a selected, initial time period after approving the credit line.

22. The computer system of claim 20 further compromising a merge component for merging a first party fraud score associated with the application, origination stage with transaction data from the post-book stage to produce a second first party fraud score associated with the origination stage and the post-book stage for the customer and one or more associated lines of credit.

23. A machine-readable medium that provides instructions that, when executed by a machine, cause the machine to:

analyze data associated with a credit line during an origination stage for predictive variables for use in a model for first party fraud;

flag an account during the origination stage when at least one or more predictive variables of first party fraud cause a fraud score to exceed a pre-described fraud likelihood threshold; and

analyze data associated with one or more previously flagged, post-booked stage credit lines for transaction based profile variables to be used as variables in a model to predict first party fraud in one or more of the post-booked stage credit lines.

24. The machine-readable medium of claim 23 that provides instructions that, when executed by a machine, further cause the machine to analyze transactions associated with the post-booked stage credit lines during a selected, initial time period after approving the credit line.

25. The machine-readable medium of claim 23 that provides instructions that, when executed by a machine, further cause the machine to merge a first party fraud score associated with the application, pre-activation stage with transaction data from the post-book stage to produce a second first party fraud score associated with the origination stage and the post-book stage.