Visualization for payment card transaction fraud analysis

• US 10,242,540 B2
• Filed: 09/02/2009
• Issued: 03/26/2019
• Est. Priority Date: 09/02/2009
• Status: Active Grant

• Current Assignee: Fair Isaac Corporation
• Original Assignee: Fair Isaac Corporation
• Inventors: Chen, Yonghui, Gancarz, Gregory, Zoldi, Scott M.
• Primary Examiner(s): Chang, Edward
• Application Number:
  US12/553,047
• Publication Number:
  US 20110055074A1
• Time in Patent Office: 3,492 Days
• Field of Search: 705 35- 40, 705 26, 705 36 R, 705 1, 705 43, 705 44, 705318
• CPC Class Codes: G06Q 20/10 specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
• 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 20/405 Establishing or using transaction specific rules
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G07F 19/201 Accessories of ATMs

Abstract

A computer-implemented method and system for visualizing card transaction fraud analysis is presented. Transaction data and account data related to one or more payment card accounts is stored in a database. The transaction data includes a fraud score. A computer processor generates one or more of a plurality of visualizations of activity of at least one suspicious account from the one or more payment card accounts for display in a graphical user interface, each of the plurality of visualizations providing at least a graphical representation of the transaction data and which is selectable from a menu provided by the computer processor in the graphical user interface. The visualizations assist in case judgment of the one or more payment cards.

Claims

1. A system comprising:

a database storing transaction data and account data related to one or more payment card accounts, the transaction data including short-term historical data and long-term historical data related to transactions executed by the one or more payment card account, the transaction data including a fraud score for one or more transactions that have a score for a set of transaction variables that exceed a threshold set by a fraud management system operatively coupled to the database via a communication network;

a computer processor that generates one or more of a plurality of visualizations of activity of at least one suspicious account from the one or more payment card accounts for display in an interactive graphical user interface, one or more of the plurality of visualizations providing at least a graphical representation of the transaction data and the fraud score selectable from a menu provided by the computer processor in the interactive graphical user interface, the plurality of visualizations including transaction data of at least one confirmed fraud account as a reference, the plurality of visualizations comprising at least one or more of a geographic map depicting the activity of the at least one suspicious account at one or more locations identified by corresponding points on the geographic map, the activity characterizing data associated with one or more of transactions at an automated teller machine (ATM), time of transactions, keyed transactions, or transactions for obtaining gas, or a time series plot depicting history of activities of the at least one suspicious account over a course of at least two or more of one day, one week, one month or other finite time span for one or more categories of transactions, such that side-by-side visual presentation of the history of activities for multiple time spans improves fraud detection capabilities; and

the interactive graphical user interface to dynamically display one or more of the plurality of visualizations, improving fraud detection capabilities of the fraud detection computing system, by further calculating a Euclidean distance between two points on a historical timeline graph for a suspicious account, wherein a calculated Euclidian distance that is closer to a known fraud cluster than to a known non-fraud cluster provides a further indication of potential fraud.

2. The system in accordance with claim 1, wherein the at least one suspicious account has a fraud score that exceeds a predetermined threshold fraud score and satisfies at least one of a plurality of expert rules criteria for case generation.

3. The system in accordance with claim 1, wherein the plurality of visualizations include a bar graph depicting the activity of the at least one suspicious account, the activity comprising a long-term historical activity and a short-term historical activity, the activity characterizing data associated with one or more transactions at an automated teller machine (ATM), time of transactions, keyed transactions, and transactions for obtaining gas.

4. The system in accordance with claim 1, wherein the plurality of visualizations include a time series plot depicting the activity of the at least one suspicious account, the time series plot dynamically displaying transaction scores for corresponding dates.

5. The system in accordance with claim 1, wherein the plurality of visualizations of activity of the at least one suspicious account further includes a visualization of activity of the confirmed fraud account.

12. The system in accordance with claim 1, wherein the plurality of visualizations comprises a histogram that represents the transaction data and the fraud score with color.

13. The system in accordance with claim 1, wherein the plurality of visualizations comprises a smoothed curve chart dynamically displaying the transaction data related to a payment card account along with the transaction data of at least one confirmed fraud account for reference.

6. A computer-implemented method comprising:

storing transaction data and account data related to one or more payment card accounts in a database of a computerized fraud detection system, the transaction data including a fraud score, short-term historical data and long-term historical data related to transactions executed by the one or more payment card accounts;

generating one or more of a plurality of visualizations of activity of at least one suspicious account from the one or more payment card accounts, at least one of the plurality of visualizations providing at least a graphical representation of the transaction data selectable from a menu provided by an interactive graphical user interface of the computerized fraud detection system, the plurality of visualizations comprising at least one or more of a geographic map depicting the activity of the at least one suspicious account at one or more locations identified by corresponding points on the geographic map, the activity characterizing data associated with;

one or more transactions at an automated teller machine (ATM), time of transactions, keyed transactions, and transactions for obtaining gas, or a time series plot depicting history of activities of the at least one suspicious account over a course of at least two or more of one day, one week, one month or other finite time span for one or more categories of transactions, such that side-by-side visual presentation of the history of activities for multiple time spans improves fraud detection capabilities; and

dynamically displaying, by the interactive graphical user interface, one or more of the plurality of visualizations, improving fraud detection capabilities of the fraud detection computing system, by further calculating a Euclidean distance between two points on a historical timeline graph for a suspicious account, wherein a calculated Euclidian distance that is closer to a known fraud cluster than to a known non-fraud cluster provides a further indication of potential fraud.

7. The method in accordance with claim 6, wherein the at least one suspicious account has a fraud score that exceeds a predetermined threshold fraud score set by a fraud management system operably coupled to the database via a communication network.

8. The method in accordance with claim 6, wherein the plurality of visualizations include transaction data of a confirmed fraud account as a reference.

9. The method in accordance with claim 6, wherein the plurality of visualizations include a bar graph depicting the activity of the at least one suspicious account.

10. The method in accordance with claim 6, wherein the plurality of visualizations include a time series plot depicting the activity of the at least one suspicious account.

11. The method in accordance with claim 9, wherein the plurality of visualizations of activity of the at least one suspicious account further includes a visualization of activity of the confirmed fraud account.

14. A non-transitory computer program product storing instructions that, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:

storing transaction data and account data related to one or more payment card accounts in a database of a computerized fraud detection system, the transaction data including a fraud score, short-term historical data and long-term historical data related to transactions executed by the one or more payment card accounts;

generating one or more of a plurality of visualizations of activity of at least one suspicious account from the one or more payment card accounts, at least one of the plurality of visualizations providing at least a graphical representation of the transaction data selectable from a menu provided by an interactive graphical user interface of the computerized fraud detection system, the plurality of visualizations comprising at least one or more of a geographic map depicting the activity of the at least one suspicious account at one or more locations identified by corresponding points on the geographic map, the activity characterizing data associated with;

one or more transactions at an automated teller machine (ATM), time of transactions, keyed transactions, and transactions for obtaining gas, or a time series plot depicting history of activities of the at least one suspicious account over a course of at least two or more of one day, one week, one month or other finite time span for one or more categories of transactions, such that side-by-side visual presentation of the history of activities for multiple time spans improves fraud detection capabilities; and

dynamically displaying, by the interactive graphical user interface, one or more of the plurality of visualizations, improving fraud detection capabilities of the fraud detection computing system, by further calculating a Euclidean distance between two points on a historical timeline graph for a suspicious account, wherein a calculated Euclidian distance that is closer to a known fraud cluster than to a known non-fraud cluster provides a further indication of potential fraud.