Methods and Systems for Dynamically Providing Content

• US 20140156411A1
• Filed: 12/05/2012
• Published: 06/05/2014
• Est. Priority Date: 12/05/2012
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Financial Corporation
• Inventors: Murgai, Nikhil
• Granted Patent: US 10,083,462 B2
• Time in Patent Office: Days
• US Class Current: 705/14.58
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute

Abstract

Systems and methods are disclosed for dynamically providing content to a user. The disclosed embodiments include generating a recommendation matrix based on event data received from a client. In certain embodiments, the client may be configured to generate event data associated with the client or a user associated with the client. The disclosed embodiments may also include generating an offer score matrix based on the recommendation matrix and the event data. In certain aspects, the offer score matrix may include score values associated with a set of offers to be provided to the user. The disclosed embodiments may identify a first offer from the set of offers based on the score values for the offers and provide an identification of the first offer. The disclosed embodiments may also receive content associated with the first offer for display on the client.

Claims

1. A device for dynamically providing content to a user, comprising:

a memory storing instructions; and

a processor configured to execute the instructions to perform operations including;

receiving a recommendation matrix from a remote computer,

generating feature data based on one or more events associated with at least one of the user and the device,

generating an offer score matrix based on the recommendation matrix and the feature data, the offer score matrix including score values associated with a set of offers to be provided to the user,

identifying a first offer from among the set of offers based on the score values associated with the set of offers,

providing an identification of the first offer, and

receiving content associated with the first offer for display on the device.

2. The device of claim 1, wherein determining the first offer includes determining that a score value associated with the first offer is higher than score values associated with other offers in the set of offers.

3. The device of claim 1, wherein generating the offer score matrix includes:

generating a feature vector based on the feature data, and

multiplying the recommendation matrix with the feature vector to generate the offer score matrix.

4. The device of claim 1, wherein the recommendation matrix includes weight values that are each associated with one of a set of offers and a trigger event.

5. The device of claim 1, wherein the processor is further configured to perform operations to send the generated feature data to the remote computer for use in updating the recommendation matrix based on the feature data.

6. The device of claim 1, wherein the processor is further configured to perform operations that include:

receiving an updated recommendation matrix from the remote computer;

generating an updated score matrix based on the updated recommendation matrix, the updated score matrix including updated score values for the offers in the set of offers; and

identifying a second offer from among the set of offers based on the updated score values.

7. The device of claim 6, wherein the processor is further configured to perform operations that include:

receiving second content relating to the second offer for display on the device.

8. The device of claim 3, wherein the feature vector includes n feature data event values and wherein generating the feature vector includes:

setting at least one feature data event value based on at least one of;

a geographic location of the device;

an indication that the user associated with the device has updated a social network parameter;

an indication that the device is traveling;

an indication that the device was used to generate a search query for an Internet-related search; and

an indication that the device is located within a determined distance from a specified geographic location.

9. The device of claim 1, wherein the processor is configured to perform operations to receive a travel graph from the remote computer, the travel graph reflecting travel movements of the device between designated geographical locations, and wherein the processor is further configured to generate at least one feature data based on the travel graph.

10. The device of claim 1, wherein the content includes content associated with at least one of an advertisement, a promotional offer, a discount, a coupon, and a sale associated with an item or service.

11. A computer-implemented method for dynamically providing content to a user, comprising:

receiving, by a device, a recommendation matrix from a remote computer;

generating, by a processor included in the device, feature data based on one or more events associated with at least one of the device and a user associated with the device;

generating, by the processor, an offer score matrix based on the recommendation matrix and the feature data, the offer score matrix including score values associated with a set of offers to be provided to the user;

identifying, by the processor, a first offer from among the set of offers based on the score values associated with the set of offers;

providing an identification of the first offer; and

receiving content associated with the first offer for display on the device.

12. The method of claim 11, wherein determining the first offer includes determining that a score value associated with the first offer is higher than score values associated with other offers in the set of offers.

13. The method of claim 11, wherein generating the offer score matrix includes:

generating a feature vector based on the feature data; and

multiplying the recommendation matrix with the feature vector to generate the offer score matrix.

14. The method of claim 11, wherein the recommendation matrix includes weight values that are each associated with one of a set of offers and a trigger event.

15. The method of claim 11, further comprising sending the generated feature data to the remote computer for use in updating the recommendation matrix based on the feature data.

16. The method of claim 11, further comprising:

receiving an updated recommendation matrix from the remote computer;

generating an updated score matrix based on the updated recommendation matrix, the updated score matrix including updated score values for the offers in the set of offers; and

identifying a second offer from among the set of offers based on the updated score values.

17. The method of claim 16, further comprising:

receiving second content relating to the second offer for display on the device.

18. The method of claim 13, wherein the feature vector includes n feature data event values and wherein generating the feature vector includes:

setting at least one feature data event value based on at least one of;

a geographic location of the device;

an indication that the user associated with the device has updated a social network parameter;

an indication that the device is traveling;

an indication that the device was used to generate a search query for an Internet-related search; and

an indication that the device is located within a determined distance from a specified geographic location.

19. A system for recommendation data associated with offers to be presented to a user, comprising:

a memory storing instructions; and

a processor configured to execute the instructions to perform operations including;

receiving customer data, the customer data including feature data provided by a remote client and corresponding to one or more events associated with the client or a user associated with the client,

generating a recommendation matrix based on the customer data and offer data associated with a set of offers to be provided to the user via the remote client, the recommendation matrix including model coefficient values corresponding to the offers in the set of offers and to events associated with the client or the user associated with the remote client, and

sending the recommendation matrix to the remote client for use in identifying a first offers from the set of offers to display on the remote client.

20. The system of claim 19, wherein the processor is further configured to perform operations including:

receiving updated feature data from the remote client;

generating an updated recommendation matrix based on the updated feature data; and

sending the updated recommendation matrix to the remote client for use in identifying a new offer from the set of offers to display on the client.