Multiple funding account payment instrument analytics

Patent metadata

Field	Value
Publication number	US-9704195-B2
Application number	US-201113198310-A
Country	US
Kind code	B2
Filing date	Aug 4, 2011
Priority date	Aug 4, 2011
Publication date	Jul 11, 2017
Grant date	Jul 11, 2017

Abstract

A system and method for multiple funding account payment instrument analytics is disclosed. A payment instrument profile is generated for a payment instrument that characterizes past activity on the payment instrument and past activity across one or more funding accounts associated with the payment instrument. Current activity on the payment instrument and current activity across one or more funding accounts associated with the payment instrument are monitored to detect an abnormality against the payment instrument profile. A fraud score for the current activity on the payment instrument and current activity across one or more funding accounts associated with the payment instrument is generated. The fraud score is based on a quantified extent of the abnormality.

First claim

The invention claimed is:

1. A computer-implemented method comprising:
receiving, using one or more processors, a payment instrument profile that characterizes past activity on a payment instrument used for a transaction and past activity across one or more funding accounts associated with the payment instrument, the one or more funding accounts being used to pay for the transaction in real time or subsequent to the transaction, data associated with the at least one funding account of the one or more funding accounts being removed from the payment instrument profile in favor of a new funding account when the at least one funding account is inactive, the at least one funding account being inactive when the at least one funding account is accessed at a frequency less than a threshold;
computing, using the one or more processors, a probability of a selected active funding account of the one or more funding accounts being used for a financial transaction that is a part of a current activity on the payment instrument and a current activity across the one or more funding accounts; and
analyzing, using the one or more processors applying a self-calibrating outlier analytics technique, the current activity on the payment instrument and the current activity across the one or more funding accounts against the probability to detect an outlier value characterizing an abnormality against the payment instrument profile.

2. The computer-implemented method in accordance with claim 1 , wherein the analyzing using the one or more processors includes: computing a favorites list of activity based on the payment instrument profile and the one or more funding accounts, the favorites list of activity representing a normalcy of behavior of a user of the payment instrument.

3. The computer-implemented method in accordance with claim 1 , wherein the analyzing using the one or more processors includes determining one or more similarities or one or more differences in behaviors of a user of the payment instrument across the one or more funding accounts.

4. A computer-implemented method comprising:
analyzing, using one or more processors of at least one computing system, past activity on a payment instrument used for one or more transactions and past activity across a plurality of funding accounts associated with the payment instrument, the plurality of funding accounts being used to pay for the one or more transactions in real time or subsequent to the one or more transactions;
generating, using the one or more processors, a payment instrument profile by compiling the past activity on a payment instrument and the past activity across the plurality of funding accounts in a single memory structure, data associated with the at least one funding account of the plurality of funding accounts being removed from the payment instrument profile in favor of a new funding account when the at least one funding account is inactive, the at least one funding account being inactive when the at least one funding account is accessed at a frequency less than a threshold; and
monitoring, using the one or more processors, current activity on the payment instrument and current activity across the plurality of funding accounts to detect an abnormality against the payment instrument profile, the abnormality being an outlier value determined by analyzing the current activity on the payment instrument and the current activity across the plurality of funding accounts against a probability of a funding account selected from the plurality of funding accounts being used for a financial transaction associated with the current activity on the payment instrument and current activity across the plurality of funding accounts.

5. The computer-implemented method in accordance with claim 4 , further comprising:
generating, using the one or more processors, a fraud score for the current activity on the payment instrument and current activity across the plurality of funding accounts, the fraud score being based on a quantified extent of the abnormality.

6. The computer-implemented method in accordance with claim 4 , wherein the payment instrument profile comprises a plurality of variables that characterize the payment instrument and the plurality of funding accounts.

7. The computer-implemented method in accordance with claim 6 , wherein the plurality of variables includes payment instrument identifier variables associated with financial and non-financial transactions performed using the payment instrument.

8. The computer-implemented method in accordance with claim 7 , wherein the plurality of variables includes cross-funding account variables that characterize patterns of use and interrelationships of each of the plurality of funding accounts.

9. The computer-implemented method in accordance with claim 8 , wherein the plurality of variables includes funding account sub-profiles that characterize patterns of use of the payment instrument when a funding account selected from the plurality of funding accounts is used in a transaction.

10. The computer-implemented method in accordance with claim 9 , further comprising quantifying, using the one or more processors, the abnormality, the quantifying being based on the plurality of variables.

11. The computer-implemented method in accordance with claim 10 , further comprising generating, using the one or more processors, a fraud score for the current activity on the payment instrument and current activity across the plurality of funding accounts, the fraud score being based on the quantifying an extent of the abnormality.

12. The computer-implemented method in accordance with claim 6 , further comprising updating, using the one or more processors, the plurality of variables based on the monitoring of current activity on the payment instrument and current activity across the plurality of funding accounts.

13. A system for multiple payment account funding analytics, the system comprising:
one or more processors; and
a tangibly embodied machine-readable medium embodying instructions that, when performed, cause the one or more processors to:
generate a payment instrument profile by compiling past activity on a payment instrument used to perform a plurality of transactions and past activity across a plurality of funding accounts associated with the payment instrument, data associated with the at least one funding account of the plurality of funding accounts being removed from the payment instrument profile in favor of a new funding account when the at least one funding account is inactive, the at least one funding account being inactive when the at least one funding account is accessed at a frequency less than a threshold; and
monitor current activity on the payment instrument and current activity across the plurality of funding accounts associated with the payment instrument to detect an abnormality against the payment instrument profile, the abnormality being an outlier value of a variable determined by analyzing the current activity on the payment instrument and the current activity across the plurality of funding accounts against a probability of a funding account selected from the plurality of funding accounts being used for a financial transaction within the current activity on the payment instrument and current activity across plurality of funding accounts associated with the payment instrument, the plurality of funding accounts being used to pay for the plurality of transactions in real time or subsequent to the plurality of transactions.

14. The computer-implemented method in accordance with claim 1 , wherein the removal of the at least one funding account in fa

Assignees

• Zoldi Scott M
• Fair Isaac Corp

Inventors

• Zoldi Scott M

Classifications

• G06Q30/0269

  based on user profile or attribute · CPC title

• G06Q40/00 Primary

  Finance; Insurance; Tax strategies; Processing of corporate or income taxes · CPC title

• G06Q30/0224

  based on user history · CPC title

• G06Q20/354

  Card activation or deactivation · CPC title

• G06Q20/3572

  Multiple accounts on card · CPC title