Estimating inventory, user behavior, and/or cost and presentation attributes for an advertisement for use with an advertising system

• US 8,224,689 B1
• Filed: 02/28/2011
• Issued: 07/17/2012
• Est. Priority Date: 01/10/2003
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Veach, Eric, Qian, Zhe, Sandberg, Magnus
• Primary Examiner(s): CHAMPAGNE, DONALD
• Application Number:
  US13/037,227
• Time in Patent Office: 505 Days
• Field of Search: 705/7.35, 705/14.42, 707/999.002, 707/999.003
• US Class Current: 705/7.35
• CPC Class Codes: G06Q 30/0206 Price or cost determination based on market factors
• CPC Class Codes: G06Q 30/0243 Comparative campaigns

Abstract

An advertiser may be provided with fast and accurate estimates of the future performance of at least one of their advertisements. These estimates may be broken down by keyword, thereby providing, up-front, useful information to the advertiser about how different keywords will affect the performance and cost of their ad campaign. Estimates and/or suggestions for a set of keywords, given additional campaign parameters, may be generated by using historical search traffic (or some other ad serving trigger) data to predict future inventory and to find useful keyword (or some other serving constraint) variations. Current data on competing ads may be used to simulate the competitions (e.g., real-time auctions) that the given ads will participate in.

Claims

1. A computer-implemented method, comprising:

receiving a candidate ad, the candidate ad associated with a plurality of keywords for triggering display of the candidate ad;

for each of the plurality of keywords, identifying a respective plurality of user queries that match the keyword according to respective matching criteria of the candidate ad; and

determining, by one or more processors, a cost estimate or presentation attribute for the candidate ad based on simulated auctions performed for a respective proportion of the respective plurality of user queries for each of the plurality of keywords, the simulated ad auctions being between the candidate ad and one or more competing ads, the respective proportion different from zero or unity.

2. The method of claim 1, wherein the respective proportion is substantially equal for each of the plurality of keywords.

3. The method of claim 1, further comprising:

for each of the plurality of keywords;

sorting the respective plurality of user queries identified for the keyword according to a respective query frequency associated with the user query; and

identifying the respective proportion of the respective plurality of user queries for the keyword from the sorted respective plurality of user queries identified for the keyword in an order of decreasing query frequency.

4. The method of claim 1, further comprising:

for each of the plurality of keywords;

determining that the respective proportion of the respective plurality of user queries for the keyword has been processed according to a stopping criterion;

5. The method of claim 1, wherein determining the cost estimate or presentation attribute for the candidate ad based on simulated auctions performed for the respective proportion of the respective plurality of user queries for each of the plurality of keywords further comprises:

processing the plurality of keywords independently of one another to obtain a cost or presentation attribute sample for the candidate ad, wherein processing each of the plurality of keywords including simulating auctions for the respective proportion of the respective plurality of user queries identified for the keyword.

6. The method of claim 1, wherein determining the cost estimate or presentation attribute for the candidate ad based simulated auctions performed for the respective proportion of the respective plurality of user queries for each of the plurality of keywords further comprises:

interlacing respective processing of each of the plurality of keywords in a plurality of iterations to obtain a cost or presentation attribute sample for the candidate ad, wherein in each iteration, an increasing number of user queries identified for each of the plurality of keywords are processed.

7. The method of claim 6, wherein a respective number of user queries processed for each keyword in each iteration doubles a respective number of user queries processed for the keyword in an immediately preceding iteration.

8. The method of claim 1, further comprising:

providing the cost estimate or presentation attribute for the candidate ad to a user through an ad management interface.

9. A computer-readable medium having instructions stored thereon, the instructions, when executed by one or more processors, cause the processors to perform operations comprising:

receiving a candidate ad, the candidate ad associated with a plurality of keywords for triggering display of the candidate ad;

for each of the plurality of keywords, identifying a respective plurality of user queries that match the keyword according to respective matching criteria of the candidate ad; and

determining, by one or more processors, a cost estimate or presentation attribute for the candidate ad based on simulated auctions performed for a respective proportion of the respective plurality of user queries for each of the plurality of keywords, the simulated ad auctions being between the candidate ad and one or more competing ads, the respective proportion different from zero or unity.

10. The computer-readable medium of claim 9, wherein the respective proportion is substantially equal for each of the plurality of keywords.

11. The computer-readable medium of claim 9, wherein the operations further comprise:

for each of the plurality of keywords;

sorting the respective plurality of user queries identified for the keyword according to a respective query frequency associated with the user query; and

identifying the respective proportion of the respective plurality of user queries for the keyword from the sorted respective plurality of user queries identified for the keyword in an order of decreasing query frequency.

12. The computer-readable medium of claim 9, wherein the operations further comprise:

for each of the plurality of keywords;

determining that the respective proportion of the respective plurality of user queries for the keyword has been processed according to a stopping criterion;

13. The computer-readable medium of claim 9, wherein determining the cost estimate or presentation attribute for the candidate ad based on simulated auctions performed for the respective proportion of the respective plurality of user queries for each of the plurality of keywords further comprises:

processing the plurality of keywords independently of one another to obtain a cost or presentation attribute sample for the candidate ad, wherein processing each of the plurality of keywords including simulating auctions for the respective proportion of the respective plurality of user queries identified for the keyword.

14. The computer-readable medium of claim 9, wherein determining the cost estimate or presentation attribute for the candidate ad based simulated auctions performed for the respective proportion of the respective plurality of user queries for each of the plurality of keywords further comprises:

interlacing respective processing of each of the plurality of keywords in a plurality of iterations to obtain a cost or presentation attribute sample for the candidate ad, wherein in each iteration, an increasing number of user queries identified for each of the plurality of keywords are processed.

15. The computer-readable medium of claim 14, wherein a respective number of user queries processed for each keyword in each iteration doubles a respective number of user queries processed for the keyword in an immediately preceding iteration.

16. The computer-readable medium of claim 9, wherein the operations further comprise:

providing the cost estimate or presentation attribute for the candidate ad to a user through an ad management interface.

17. A system, comprising:

one or more processors; and

memory having instructions stored thereon, the instructions, when executed by the one or more processors, cause the processors to perform operations comprising;

receiving a candidate ad, the candidate ad associated with a plurality of keywords for triggering display of the candidate ad;

for each of the plurality of keywords, identifying a respective plurality of user queries that match the keyword according to respective matching criteria of the candidate ad; and

determining, by one or more processors, a cost estimate or presentation attribute for the candidate ad based on simulated auctions performed for a respective proportion of the respective plurality of user queries for each of the plurality of keywords, the simulated ad auctions being between the candidate ad and one or more competing ads, the respective proportion different from zero or unity.

18. The system of claim 17, wherein the respective proportion is substantially equal for each of the plurality of keywords.

19. The system of claim 17, wherein the operations further comprise:

for each of the plurality of keywords;

sorting the respective plurality of user queries identified for the keyword according to a respective query frequency associated with the user query; and

identifying the respective proportion of the respective plurality of user queries for the keyword from the sorted respective plurality of user queries identified for the keyword in an order of decreasing query frequency.

20. The system of claim 17, wherein the operations further comprise:

for each of the plurality of keywords;

determining that the respective proportion of the respective plurality of user queries for the keyword has been processed according to a stopping criterion;

21. The system of claim 17, wherein determining the cost estimate or presentation attribute for the candidate ad based on simulated auctions performed for the respective proportion of the respective plurality of user queries for each of the plurality of keywords further comprises:

processing the plurality of keywords independently of one another to obtain a cost or presentation attribute sample for the candidate ad, wherein processing each of the plurality of keywords including simulating auctions for the respective proportion of the respective plurality of user queries identified for the keyword.

22. The system of claim 17, wherein determining the cost estimate or presentation attribute for the candidate ad based simulated auctions performed for the respective proportion of the respective plurality of user queries for each of the plurality of keywords further comprises:

interlacing respective processing of each of the plurality of keywords in a plurality of iterations to obtain a cost or presentation attribute sample for the candidate ad, wherein in each iteration, an increasing number of user queries identified for each of the plurality of keywords are processed.

23. The system of claim 22, wherein a respective number of user queries processed for each keyword in each iteration doubles a respective number of user queries processed for the keyword in an immediately preceding iteration.

24. The system of claim 17, wherein the operations further comprise:

providing the cost estimate or presentation attribute for the candidate ad to a user through an ad management interface.