USING USER SEARCH BEHAVIOR TO PLAN ONLINE ADVERTISING CAMPAIGNS

• US 20090157676A1
• Filed: 12/17/2007
• Published: 06/18/2009
• Est. Priority Date: 12/17/2007
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: SHANBHAG, Amit Umesh
• Granted Patent: US 8,452,768 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0256 User search

Abstract

Targeting parameters are generated for a media buy plan for advertisements to be displayed in conjunction with presenting web pages, based on a history of search events. Key phrases are received relative to a subject of the advertisements to be displayed. The received key phrases are provided as proposed key phrases to determine, from search events indicative of historical data of uses of a search service, a first subportion of search events for queries of the search service with the proposed key phrases and a second subportion of search events for queries of the search service not with the proposed key phrases. Classification processing is applied to determine potential targeting parameters associated with the first subportion and with the second subportion to identify potential targeting parameters that, statistically, contribute to membership in the first sub-population and in the second sub-population, respectively. Statistics are associated with the potential targeting parameters, based on the historical data, indicative of factors usable to determine whether to use the potential targeting parameters as actual targeting parameters of the media buy plan.

Claims

1. A method of generating targeting parameters of a media buy plan for advertisements to be displayed in conjunction with presenting web pages, based on a history of search events, comprising:

receiving key phrases relative to a subject of the advertisements to be displayed;

providing the received key phrases as proposed key phrases to determine, from search events indicative of historical data of uses of a search service, a first subportion of search events for queries of the search service with the proposed key phrases and a second subportion of search events for queries of the search service not with the proposed key phrases;

applying classification processing to determine potential targeting parameters associated with the first subportion and with the second subportion to identify potential targeting parameters that, statistically, contribute to membership in the first sub-population and in the second sub-population, respectively; and

associating statistics with the potential targeting parameters, based on the historical data, indicative of factors usable to determine whether to use the potential targeting parameters as actual targeting parameters of the media buy plan.

2. The method of claim 1, further comprising:

processing the received key phrases with a key phrase expansion processing to determine the proposed key phrases, such that at least a portion of the expanded key phrases comprises the received key phrases.

3. The method of claim 1, wherein:

a result of the classification processing includes a decision tree of the potential targeting parameters.

4. The method of claim 3, wherein:

the decision tree of the proposed targeting parameters includes a plurality of nodes, each node corresponding to one or more of the potential targeting parameters, and the classification processing includes determining, for at least some of the nodes, statistics of the classification relative to the one or more of the potential targeting parameters to which that node corresponds.

5. The method of claim 1, wherein:

the classification processing includes determining, for each at least some of the nodes, statistics regarding the one or more potential targeting parameters to which that node corresponds.

6. The method of claim 1, further comprising:

examining the potential targeting parameters determined in the classification processing, relative to the received initial key phrases, in view of costs associated with a media buy relative to those potential targeting parameters, to generate recommendations regarding the media buy plan relative to at least some of the potential targeting parameters.

7. The method of claim 6, wherein:

examining the potential targeting parameters determined in the classification processing is further relative to a budget for the media buy.

8. The method of claim 1, wherein:

generating the statistics includes generating recall and precision statistics based on the classification processing.

9. The method of claim 1, further comprising:

estimating a cost of using the targeting parameters based on expected impressions of the advertisements to be displayed.

10. The method of claim 9, wherein:

estimating the cost of using the targeting parameters is further based on estimated costs of the impressions.

11. A computer program product for generating targeting parameters of a media buy plan for advertisements to be displayed in conjunction with presenting web pages, based on a history of search events, the computer program product comprising at least one computer-readable medium having computer program instructions stored therein which are operable to cause at least one computing device to:

receive key phrases relative to a subject of the advertisements to be displayed;

provide the received key phrases as proposed key phrases to determine, from search events indicative of historical data of uses of a search service, a first subportion of search events for queries of the search service with the proposed key phrases and a second subportion of search events for queries of the search service not with the proposed key phrases;

apply classification processing to determine potential targeting parameters associated with the first subportion and with the second subportion to identify potential targeting parameters that, statistically, contribute to membership in the first sub-population and in the second sub-population, respectively; and

associate statistics with the potential targeting parameters, based on the historical data, indicative of factors usable to determine whether to use the potential targeting parameters as actual targeting parameters of the media buy plan.

12. The computer program product of claim 11, wherein:

the computer program instructions further include computer program instructions operable to cause the at least one computing device to process the received key phrases with a key phrase expansion processing to determine the proposed key phrases, such that at least a portion of the expanded key phrases comprises the received key phrases.

13. The computer program product of claim 11, wherein:

a result of the classification processing includes a decision tree of the potential targeting parameters.

14. The computer program product of claim 13, wherein:

the decision tree of the proposed targeting parameters includes a plurality of nodes, each node corresponding to one or more of the potential targeting parameters, and the classification processing includes determining, for at least some of the nodes, statistics of the classification relative to the one or more of the potential targeting parameters to which that node corresponds.

15. The computer program product of claim 11, wherein:

the classification processing program instructions includes program instructions to, for each at least some of the nodes, generate statistics regarding the one or more potential targeting parameters to which that node corresponds.

16. The computer program product of claim 11, wherein:

the computer program instructions further include computer program instructions operable to cause the at least one computing device to examine the potential targeting parameters determined in the classification processing, relative to the received initial key phrases, in view of costs associated with a media buy relative to those potential targeting parameters, to generate recommendations regarding the media buy plan relative to at least some of the potential targeting parameters.

17. The computer program product of claim 16, wherein:

examining the potential targeting parameters determined in the classification processing is further relative to a budget for the media buy.

18. The computer program product of claim 11, wherein:

generating the statistics includes generating recall and precision statistics based on the classification processing.

19. The computer program product of claim 11, wherein:

the computer program instructions further include computer program instructions operable to cause the at least one computing device to estimate a cost of using the targeting parameters based on expected impressions of the advertisements to be displayed.

20. The computer program product of claim 19, wherein:

estimating the cost of using the targeting parameters is further based on estimated costs of the impressions.

21. A computing system including at least one computing device, configured to generate targeting parameters of a media buy plan for advertisements to be displayed in conjunction with presenting web pages, based on a history of search events, the at least one computing device configured to:

receive key phrases relative to a subject of the advertisements to be displayed;

provide the received key phrases as proposed key phrases to determine, from search events indicative of historical data of uses of a search service, a first subportion of search events for queries of the search service with the proposed key phrases and a second subportion of search events for queries of the search service not with the proposed key phrases;

apply classification processing to determine potential targeting parameters associated with the first subportion and with the second subportion to identify potential targeting parameters that, statistically, contribute to membership in the first sub-population and in the second sub-population, respectively; and

associate statistics with the potential targeting parameters, based on the historical data, indicative of factors usable to determine whether to use the potential targeting parameters as actual targeting parameters of the media buy plan.

22. The computing system of claim 21, wherein:

a result of the classification processing includes a decision tree of the potential targeting parameters.

23. The computing system of claim 22, wherein:

the decision tree of the proposed targeting parameters includes a plurality of nodes, each node corresponding to one or more of the potential targeting parameters, and the classification processing includes determining, for at least some of the nodes, statistics of the classification relative to the one or more of the potential targeting parameters to which that node corresponds.

24. The computing system of claim 21, wherein:

the classification processing includes determining, for each at least some of the nodes, statistics regarding the one or more potential targeting parameters to which that node corresponds.

25. The computing system of claim 21, wherein the at least one computing device is further configured to:

examine the potential targeting parameters determined in the classification processing, relative to the received initial key phrases, in view of costs associated with a media buy relative to those potential targeting parameters, to generate recommendations regarding the media buy plan relative to at least some of the potential targeting parameters.