Selecting advertisements based on advertising revenue model

• US 8,655,730 B1
• Filed: 09/28/2011
• Issued: 02/18/2014
• Est. Priority Date: 09/28/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Zhang, Zhuo, Brighton, Mark E., Swan, Charles D., Edwards, Brent E.
• Primary Examiner(s): Weiss, John G
• Assistant Examiner(s): Patel, Dipen
• Application Number:
  US13/247,486
• Time in Patent Office: 874 Days
• Field of Search: 705/14.69
• US Class Current: 705/14.69
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

Advertising revenue may be optimized by selecting an advertisement to display to a user based at least in part on the user'"'"'s browsing history and a revenue model associated with the advertisement. For example, if the user has a relatively high clicking frequency on advertisements, then pay-per-click advertisements may be selected for presentation to the user rather than pay-per-impression advertisements. Revenue model-based advertisement selection may be combined with other advertising techniques, such as targeting.

Claims

1. A method of providing advertisements, the method comprising:

receiving an advertisement request from a web browser, the advertisement request being associated with a web page to be rendered by the browser for display to a user;

identifying at least one pay-per-click advertisement in response to the advertisement request;

identifying at least one pay-per-impression advertisement in response to the advertisement request;

identifying a browse history of the user, the browse history comprising information regarding a clicking frequency of the user on first advertisements other than the at least one pay-per-click advertisement and the at least one pay-per-impression advertisement;

determining whether the clicking frequency of the user meets a threshold;

selecting a second advertisement, said selecting comprising;

in response to the clicking frequency of the user meeting the threshold, selecting the at least one pay-per-click advertisement as the second advertisement;

in response to the clicking frequency of the user not meeting the threshold, selecting the at least one pay-per-impression advertisement as the second advertisement; and

providing the second advertisement to the browser for display on the web page;

wherein at least said identifying the browse history and determining whether the clicking frequency meets the threshold are performed by one or more computer systems comprising one or more computers.

2. The method of claim 1, wherein the threshold is an inverse of a ratio of revenue-per-click to revenue-per-impression.

3. The method of claim 1, further comprising:

identifying, based at least in part on the browse history of the user, at least one pay-per-acquisition advertisement that may be displayed to the user in response to the advertisement request; and

outputting the pay-per-acquisition advertisement for presentation to the user.

4. The method of claim 1, wherein the user'"'"'s past interaction with the first advertisements is weighted over time.

5. The method of claim 1, wherein the user'"'"'s past interaction with the first advertisements comprises past interaction with advertisements of a user group that has similar characteristics as the user.

6. The method of claim 1, wherein said selecting the selected advertisement is further based at least in part on past purchases of the user.

7. The method of claim 1, wherein said selecting the selected advertisement is further based at least in part on an average session length of the user.

8. The method of claim 1, wherein the advertisements comprise advertisements that are associated with a web page, a social network or an electronic message.

9. A system for providing advertisements, the system comprising:

at least one computing device configured to implement one or more advertisement services, wherein the one or more advertisement services are configured to;

receive an advertisement request to provide an advertisement for presentation to a user;

identify at least one pay-per-click advertisement in response to the advertisement request;

identify at least one pay-per-impression advertisement in response to the advertisement request;

identify a browse history of the user, the browse history comprising information regarding a clicking frequency of the user on first advertisements other than the at least one pay-per-click advertisement and the at least one pay-per-impression advertisement;

compare the clicking frequency of the user with a threshold; and

select, for presentation to the user, the at least one pay-per-click advertisement or the at least one pay-per-impression advertisement based on the comparison of the clicking frequency of the user with the threshold.

10. The system of claim 9, wherein the threshold is an inverse of a ratio of revenue-per-click to revenue-per-impression.

11. The system of claim 9, wherein the advertisement service is further configured to:

identify, based at least in part on the browse history of the user, at least one pay-per-acquisition advertisement that may be displayed to the user in response to the advertisement request; and

output the pay-per-acquisition advertisement for presentation to the user.

12. The system of claim 9, wherein the user'"'"'s browse history is weighted over time.

13. The system of claim 9, wherein the user'"'"'s browse history comprises past interaction with advertisements of a user group that has similar characteristics as the user.

14. The system of claim 9, wherein the advertisement service is further configured to select the selected advertisement based at least in part on past purchases of the user.

15. The system of claim 9, wherein the advertisement service is further configured to select the selected advertisement based at least in part on an average session length of the user.

16. The system of claim 9, wherein the advertisements comprise advertisements that are associated with one or more of the following:

a web page, a social network, or an electronic message.

17. The system of claim 9, wherein the one or more advertisement services are further configured to select the selected advertisement based at least in part on a session length of the user.

18. The system of claim 9, wherein the one or more advertisement services are further configured to select the selected advertisement based at least in part on an average session length of the user.

22. The non-transitory physical computer storage of claim 17, wherein the user'"'"'s browse history comprises past interaction with advertisements of a user group that has similar characteristics as the user.

23. The non-transitory physical computer storage of claim 17, wherein the advertisement service is further configured to select the selected advertisement based at least in part on a session length of the user.

24. The non-transitory physical computer storage of claim 17, wherein the advertisement service is further configured to select the selected advertisement based at least in part on an average session length of the user.

19. Non-transitory physical computer storage comprising computer-executable instructions stored thereon that, when implemented by one or more hardware processors, are configured to implement one or more advertisement services, wherein the one or more advertisement services are configured to:

identify at least one pay-per-click advertisement;

identify at least one pay-per-impression advertisement;

identify a browse history of a user, the browse history comprising user information regarding a clicking frequency of the user on first advertisements other than the at least one pay-per-click advertisement and the at least one pay-per-impression advertisement;

based on the user information, select either the at least one pay-per-click advertisement or the at least one pay-per-impression advertisement; and

output the selected advertisement for presentation to the user.

20. The non-transitory physical computer storage of claim 19, wherein the advertisement service is further configured to select the selected advertisement by comparing the user information to a threshold, wherein the threshold is an inverse of a ratio of revenue-per-click to revenue-per-impression.

21. The non-transitory physical computer storage of claim 19, wherein the user'"'"'s browse history is weighted over time.