DYNAMIC NETWORK ANALYTICS SYSTEM

• US 20130144888A1
• Filed: 12/05/2012
• Published: 06/06/2013
• Est. Priority Date: 12/05/2011
• Status: Active Grant

• Current Assignee: Visa International Service Association (Visa, Inc.)
• Original Assignee: Visa International Service Association (Visa, Inc.)
• Inventors: Faith, Patrick, Harris, Theodore, O'Connell, Craig, Siegel, Kevin P.
• Granted Patent: US 9,348,896 B2
• Time in Patent Office: Days
• US Class Current: 707/748
• CPC Class Codes: G06F 16/338 Presentation of query results
• 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

Abstract

Embodiments of the invention is directed to a dynamic network analytics system capable of receiving and analyzing queries sent in data messages from data requesters. The queries contain a request from the data requester as to a risk level associated with an interaction conducted by a user. The dynamic network analytics system can determine an optimized process for determining the risk level of the interaction, based on an analysis of past interactions by the user and past interactions by users similar to the user. The dynamic network analytics system can retrieve data from internal and external data sources to generate a response to the query. The dynamic network analytics system conducts the optimized process and uses the retrieved data to generate risk assessments and risk scores in response to the query from the data requester.

Claims

1. A method comprising:

receiving, at a data analyzer module, a first data message including a query from a data requester;

determining, by the data analyzer module, a current risk level associated with the query;

receiving, at the data analyzer module, risk data relevant to the query from one or more fixed risk data tables and one or more dynamic risk data tables;

receiving, at the data analyzer module, external data relevant to the query from a first external data source;

determining, at the data analyzer module, whether there is sufficient data to form a response to the query or one or more cut-off values have been reached, wherein if there is insufficient data or one or more cut-off values have not been reached, retrieving external data relevant to the query from a second external data source until there is sufficient data to form a response to the query or one or more cut-off values have been reached;

generating, at the data analyzer module, a second data message containing the response to the query; and

providing the second data message to the data requester.

2. The method of claim 1 wherein the query is based on an interaction by a user with the data requester and comprises at least one of device data, consumer data, interaction data, and transaction data.

3. The method of claim 1 wherein determining whether there is sufficient data to form the response to the query is based on a balancing of the current risk level, a cost of querying each of the plurality of external data sources, and a time to query each of the plurality of external data sources.

4. The method of claim 1 further comprising:

evaluating, by the data analyzer module, interaction history related to the query.

5. The method of claim 1 wherein the response comprises a risk assessment for the query.

6. The method of claim 1 wherein the response is based on the data received from one or more of the one or more fixed risk data tables, one or more dynamic risk data tables, and the external data sources.

7. The method of claim 1 wherein the one or more cut-off values are time-based, cost-based or accuracy-based.

8. A method comprising:

receiving, at a data analyzer module, a first data message including a query from a data requester;

parsing the query to determine current interaction data for an interaction conducted by the consumer with the data requester system;

retrieving stored consumer data, wherein the stored consumer data comprises past interaction data by the consumer with the data requester system;

retrieving stored similar consumers data, wherein the stored similar consumers data comprises risk levels for the interaction for similar consumers to the consumer;

retrieving stored external sources data;

determining, based on the stored consumer data, the stored similar consumers data, and the stored external sources data, a current risk level associated with the interaction conducted by the consumer with the data requester system; and

determining a process for querying a plurality of external data sources.

9. The method of claim 8 wherein determining the process for querying a plurality of external data sources comprises:

evaluating the stored external sources data with the current risk level associated with the interaction conducted by the consumer with the data requester system; and

determining a selection of the plurality of external data sources to retrieve data from related to the query.

10. The method of claim 9 wherein the stored external sources data is comprised of at least a cost of querying each one of the plurality of external data sources, a time required to receive a response from each one of the plurality of external data sources, and a reliability score for each one of the plurality of external data sources.

11. The method of claim 10 further comprising:

updating the stored consumer data with the current interaction data; and

updating the stored similar consumers data with the current risk level associated with the interaction conducted by the consumer with the data requester system.

12. A method comprising:

receiving a request for an estimate of risk concerning a consumer;

determining a first risk level estimate concerning the consumer using a first set of data;

determining a first value representing a confidence in the first risk level estimate;

ascertaining a cost of acquiring a second set of data for determining another risk estimate concerning the consumer;

automatically weighing, using at least one processor operatively coupled with a memory, the first value representing a confidence against the cost of acquiring the second set of data;

automatically acquiring the second set of data based on the automatic weighing;

updating the first risk level estimate to a second risk level estimate concerning the consumer using the automatically acquired second set of data; and

sending a response to the request.

13. The method of claim 12 further comprising:

determining a second value representing a confidence in the second risk level estimate,

wherein the sending is based on the second value representing a confidence in the second risk level estimate.

14. The method of claim 13 further comprising:

ascertaining a cost of acquiring a third set of data for determining another risk estimate concerning the consumer; and

automatically weighing the second value representing a confidence in the second risk level estimate against the cost of acquiring the third set of data.

15. The method of claim 14 further comprising:

automatically acquiring the third set of data based on the automatic evaluating;

updating the second risk level estimate to a third risk level estimate concerning the consumer using the automatically acquired third set of data;

determining a third value representing a confidence in the third risk level estimate;

ascertaining a cost of acquiring a fourth set of data for determining another risk estimate concerning the consumer;

automatically assessing the third value representing a confidence in the third risk level estimate against the cost of acquiring the fourth set of data,

wherein the sending is based on the automatic evaluation.

16. The method of claim 12 wherein the cost is ascertained from a table.

17. The method of claim 12 wherein the cost is selected from the group consisting of a time and a monetary amount.

18. The method of claim 12 wherein the second set of data is acquired from an external data source.

19. The method of claim 12 wherein the first set of data includes a risk data table.

20. The method of claim 19 wherein the risk data table is a fixed risk data table or a dynamic risk data table.