Learning Display Parameters to Maximize Advertising Revenue

• US 20110313845A1
• Filed: 06/18/2010
• Published: 12/22/2011
• Est. Priority Date: 06/18/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Richardson, Matthew, Bal, Hrishikesh, Bilenko, Mikhail, Dominowska, Ewa, Bapna, Deepak, Crispo, Anthony, Gupta, Arunesh, Kauhanen, Marty, Schult, Scott
• Granted Patent: US 10,373,193 B2
• Time in Patent Office: Days
• US Class Current: 705/14.42
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• CPC Class Codes: G06Q 30/0244 Optimization

Abstract

In one embodiment, an evolving advertising system automatically optimizes internet advertising. A data storage unit 250 may store an evolving advertisement unit 320 with an advertisement characteristic according to an initial configuration parameter. A communication interface 280 may transmit the evolving advertisement unit 320 as part of a primary website 310. A processor 220 may alter the evolving advertisement unit 320 automatically upon a trigger event by changing the advertisement characteristic to follow an automatically generated configuration parameter to optimize an advertisement performance metric.

Claims

1. A machine-implemented method for automatically optimizing web advertising, comprising:

creating an evolving advertisement unit with an advertisement characteristic according to an initial configuration parameter;

displaying the evolving advertisement unit on a primary website;

altering the evolving advertisement unit automatically upon a trigger event by changing the advertisement characteristic to follow an automatically generated configuration parameter to optimize an advertisement performance metric.

2. The method of claim 1, further comprising:

determining the initial configuration parameter based on an initial test performance result by a test set of advertisement units.

3. The method of claim 1, further comprising:

creating the automatically generated configuration parameter based on a test performance result by a test set of advertisement units.

4. The method of claim 3, wherein the test performance result is based off a parallel test run on the test set of advertisement units.

5. The method of claim 1, further comprising:

assigning a site profile to the primary website;

creating the automatically generated configuration parameter based on the site profile.

6. The method of claim 1, further comprising:

assigning a user profile to a user viewing the primary website;

creating the automatically generated configuration parameter based on the user profile.

7. The method of claim 1, further comprising:

creating the automatically generated configuration parameter using machine learning.

8. The method of claim 1, further comprising:

creating the automatically generated configuration parameter based on a seasonal characteristic.

9. The method of claim 1, further comprising:

applying a configuration constraint on the automatically generated configuration parameter.

10. The method of claim 1, further comprising:

collecting an explicit advertisement performance metric.

11. The method of claim 1, further comprising:

determining an implicit advertisement performance metric.

12. A tangible machine-readable medium having a set of instructions detailing a method stored thereon that when executed by one or more processors cause the one or more processors to perform the method, the method comprising:

displaying an evolving advertisement unit with an advertisement characteristic according to an initial configuration parameter on a primary website; and

altering the evolving advertisement unit automatically upon a trigger event by changing the advertisement characteristic to follow an automatically generated configuration parameter to optimize an advertisement performance metric.

13. The tangible machine-readable medium of claim 12, wherein the method further comprises:

creating the automatically generated configuration parameter based on a parallel test run on a test set of advertisement units.

14. The tangible machine-readable medium of claim 12, wherein the method further comprises:

assigning a site profile to the primary website;

creating the automatically generated configuration parameter based on the site profile.

15. The tangible machine-readable medium of claim 12, wherein the method further comprises:

assigning a user profile to a user viewing the primary website;

creating the automatically generated configuration parameter based on the user profile.

16. The tangible machine-readable medium of claim 12, wherein the method further comprises:

creating the automatically generated configuration parameter using machine learning.

17. The tangible machine-readable medium of claim 12, wherein the method further comprises:

applying a configuration constraint on the automatically generated configuration parameter.

18. An advertisement server that provides internet advertising, comprising:

a data storage unit that stores an evolving advertisement unit with an advertisement characteristic according to an initial configuration parameter;

a network interface that transmits the evolving advertisement unit as part of a primary website;

a database interface that connects to a database storing a test performance result from a parallel test run on a test set of advertisement units; and

a processor that alters the evolving advertisement unit automatically upon a trigger event by changing the advertisement characteristic to follow an automatically generated configuration parameter based on a test performance result to optimize an advertisement performance metric.

19. The advertisement server of claim 18, wherein the network receives an explicit advertisement performance metric from a user.

20. The advertisement server of claim 18, wherein the processor creates the automatically generated configuration parameter using machine learning.