System and method for presenting multivariate information

• US 10,204,376 B2
• Filed: 10/20/2010
• Issued: 02/12/2019
• Est. Priority Date: 10/20/2010
• Status: Active Grant

• Current Assignee: Fis Financial Compliance Solutions LLC (Fidelity National Information Services Incorporated)
• Original Assignee: Fis Financial Compliance Solutions LLC (Fidelity National Information Services Incorporated)
• Inventors: Leibon, Gregory David, Harris, Katherine Beck, Waks, Mark Jeffrey
• Primary Examiner(s): Ouellette, Jonathan P
• Application Number:
  US12/908,683
• Publication Number:
  US 20120101828A1
• Time in Patent Office: 3,037 Days
• Field of Search: 705 44, 705 11-912, 726 7
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 20/4016 involving fraud or risk level assessment in transaction processing
• CPC Class Codes: G06Q 30/0185 Product, service or business identity fraud
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03

Abstract

Systems and methods for presenting fraud detection information are presented. In one example, a computer system analyzes empirical data to detect potentially fraudulent activity and alerts users of the potentially fraudulent activity via a fraud detection user interface. The fraud detection user interface determines a set of user interface components to suitable to present the potentially fraudulent activity and presents facts associated with the potentially fraudulent activity to a user for further analysis and investigation.

Claims

1. A computer system for detecting fraudulent activity comprising:

a memory storing data describing a suspect activity including a plurality of attributes and a plurality of authentic activities including a plurality of authentic attribute values,

each attribute of the plurality of attributes comprising an actual value and being associated with an expected value, and each of the plurality of authentic activities sharing at least one common characteristic with the suspect activity, the plurality of authentic attribute values having a standard deviation; and

an interface coupled to the memory to;

receive, from an analytics engine, a fraud alert comprising an indication of the suspect activity;

determine at least one reason code, at least in part, based on parsing the fraud alert;

correlate, using a data structure, the at least one reason code with at least one user interface component;

select the at least one user interface component based on the fraud alert and the correlating of the at least one reason code; and

present a representation of differences using the at least one selected user interface component, the representation comprising a plurality of axes, each axis indicating a set of potential values for a difference between the actual value of, and the expected value associated with, each attribute of the plurality of attributes of the suspect activity,

wherein the representation of differences includes at least one geometric shape that represents a set of reference values, the at least one geometric shape including a plurality of concentric circles, and

wherein each of the plurality of concentric circles has a center, a circumference and a radius with a distance indicating that a value represented by the center differs from a value represented by any point on the circumference by a multiple of the standard deviation.

2. The system according to claim 1, wherein the at least one geometric shape includes a circle.

3. The system according to claim 1, wherein the at least one geometric shape includes a three dimensional shape.

4. The system according to claim 1, wherein the interface is further configured to present a representation using the at least one selected user interface component of at least one authentic activity that shares a common characteristic with the suspect activity.

5. The system according to claim 1, wherein the data describing the suspect activity includes information describing presentation of a check.

6. The system according to claim 5, wherein the plurality of axes includes a first axis and a second axis,

the first axis indicating a set of potential values for a serial number of the check, and

the second axis indicating a set of potential values for the amount of the check.

7. The system according to claim 6, wherein the set of potential values on each axis indicate standard deviations of the expected value of each attribute.

8. The system according to claim 7, wherein the standard deviations of the expected value of each attribute are calculated based on authentic checks associated with the account.

9. A computer implemented method for detecting fraudulent activity, the method comprising:

storing, using a processor, data describing a suspect activity in a memory, the suspect activity including a plurality of attributes, each attribute of the plurality of attributes including an actual value and being associated with an expected value;

storing, using the processor, data describing a plurality of authentic activities including a plurality of authentic attribute values, each of the plurality of authentic activities sharing at least one common characteristic with the suspect activity, the plurality of authentic attribute values having a standard deviation;

receiving, from an analytics engine, a fraud alert comprising an indication of the suspect activity;

determine at least one reason code, at least in part, based on parsing the fraud alert;

correlating, using a data structure, the at least one reason code with at least one user interface component;

selecting at least one user interface component based on the fraud alert and the correlating of the at least one reason code; and

presenting a representation of differences using the at least one selected user interface component, the representation comprising a plurality of axes, each axis indicating a set of potential values for a difference between the actual value of, and the expected value associated with, each attribute of the plurality of attributes of the suspect activity,

wherein presenting the representation of differences using the at least one selected user interface component includes presenting at least one geometric shape that represents at least one set of reference values, and

wherein the at least one geometric shape includes presenting a plurality of concentric circles, each of the plurality of concentric circles having a center, a circumference and a radius with a distance indicating that value represented by the center of the circle differs from a value represented by any point on the circumference by a multiple of the standard deviation.

10. The method according to claim 9, wherein presenting the at least one geometric shape includes presenting a circle.

11. The method according to claim 9, wherein presenting the at least one geometric shape includes presenting a three dimensional shape.

12. The method according to claim 9, further comprising presenting a representation using the at least one selected user interface component of at least one authentic activity that shares a common characteristic with the suspect activity.

13. The method according to claim 9, wherein storing the data describing the suspect activity includes storing information describing presentation of a check.

14. A non-transitory computer readable medium having instructions stored thereon that, when executed by at least one processor, instruct the at least one processor to perform a method for detecting potentially fraudulent activity, the method comprising:

storing data describing a suspect activity, the suspect activity including a plurality of attributes, each attribute of the plurality of attributes including an actual value and being associated with an expected value;

storing data describing a plurality of authentic activities including a plurality of authentic attribute values, each of the plurality of authentic activities sharing at least one common characteristic with the suspect activity, the plurality of authentic attribute values having a standard deviation;

receiving, from an analytics engine, a fraud alert comprising an indication of the suspect activity;

determining at least one reason code, at least in part, based on parsing the fraud alert;

correlating, using a data structure, the at least one reason code with at least one user interface component in association with presentation of the fraud alert;

selecting at least one user interface component based on the fraud alert and the correlating of the at least one reason code; and

presenting a representation of differences using the at least one selected user interface component, the representation including a plurality of axes, each axis indicating a set of values for a difference between the actual value of, and the expected value associated with, each attribute of the plurality of attributes of the suspect activity, the representation of differences including at least one geometric shape that represents at least one set of reference values, and

wherein the at least one geometric shape comprises a plurality of concentric circles, each of the plurality of concentric circles having a center, a circumference and a radius with a distance indicating that a value represented by the center of the circle differs from a value represented by any point on the circumference by a multiple of the standard deviation.