Pacing objectives of an advertising campaign throughout a duration of the advertising campaign

• US 10,325,283 B2
• Filed: 01/24/2014
• Issued: 06/18/2019
• Est. Priority Date: 01/24/2014
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Karande, Chinmay Deepak, Jiang, Xiaohu, Zhu, Zhengyong
• Primary Examiner(s): Schmucker, Michael W
• Application Number:
  US14/164,086
• Publication Number:
  US 20150213488A1
• Time in Patent Office: 1,971 Days
• Field of Search: None
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: G06Q 30/0249 based upon budgets or funds

Abstract

An advertiser specifies an advertising campaign along with a budget, a duration and one or more objectives associated with the advertising campaign. An online system presenting advertisements from the advertising campaign determines an interval representing a portion of the duration, an interval budget, and one or more interval objectives. Historical information describing selection and presentation of advertisements by the online system is retrieved, and used to determine one or more filters limiting the number of opportunities to present an advertisement in which advertisements from the advertising campaign are included. The scaling filters may be based on the one or more interval objectives, bid amounts determined for advertisements in the advertising campaign, and bid amounts associated with advertisements previously selected for presentation form the historical data.

Claims

1. A method comprising:

receiving information for an advertising campaign including one or more advertisements for presentation to one or more users of a social networking system, the advertising campaign associated with a budget, an impression objective, and a reach objective;

determining an interval impression objective specifying a first portion of the impression objective to be completed in an interval of the advertising campaign based at least in part on a predicted performance of the advertising campaign during the interval, the interval representing a portion of the duration of the advertising campaign;

determining an interval reach objective specifying a first portion of the reach objective to be completed in the interval based at least in part on the predicted performance of the advertising campaign;

determining, by a computer, one or more scaling filters based at least in part on a combination of the interval impression objective, the interval reach objective, the budget, and the performance of the advertising campaign, the one or more scaling filters being usable to select of one or more advertisements of the advertising campaign for inclusion in advertisement auctions;

during a first interval;

identifying a first plurality of opportunities to present advertisements to users of the social networking system,

determining whether to include one or more advertisements from the advertising campaign in auctions associated with the first plurality of identified opportunities based at least in part on the one or more scaling filters;

tracking, by the computer, a performance of the advertising campaign, the performance describing an impression count and a reach count from a start time of the advertising campaign, the impression count counting times an advertisement from the advertising campaign was presented to users of the social networking system and the reach count counting different users of the social networking system that were presented with an advertisement from the advertising campaign;

determining an updated interval impression objective specifying a second portion of the impression objective to be completed in a new interval of the advertising campaign based at least in part on the performance of the advertising campaign during the first interval;

determining an updated interval reach objective specifying a second portion of the reach objective to be completed in the new interval based at least in part on the performance of the advertising campaign during the first interval;

modifying, by the computer, the one or more scaling filters based at least in part on a combination of the updated interval impression objective and the updated interval reach objective; and

during the new interval;

identifying a second plurality of opportunities to present advertisements to users of the social networking system,

determining whether to include one or more advertisements from the advertising campaign in auctions associated with the second plurality of identified opportunities based at least in part on the one or more modified scaling filters.

2. The method of claim 1, further comprising:

determining the predicted performance of the advertising campaign, the predicted performance describing a predicted number of impressions during the interval and a predicted amount of reach during the interval.

3. The method of claim 2, wherein determining the predicted performance of the advertising campaign, the predicted performance describing the predicted number of impressions during the interval and the predicted amount of reach during the interval comprises:

retrieving information describing previously completed auctions selecting one or more advertisements for presentation to users, the retrieved information including bid amounts associated with advertisements in the previously completed auctions; and

determining a number of the previously completed auctions in which an advertisement from the advertising campaign would have been selected, based at least in part on the retrieved information and bid amounts associated with advertisements in the advertising campaign.

4. The method of claim 2, wherein determining the predicted performance of the advertising campaign, the predicted performance describing the predicted number of impressions during the interval and the predicted amount of reach during the interval comprises:

determining a pacing factor based on an amount received from an advertiser associated with the advertising campaign at a start of the interval and the budget associated with the advertising campaign;

modifying bid amounts associated with advertisements in the advertising campaign based at least in part on the pacing factor;

retrieving information describing previously completed auctions selecting one or more advertisements for presentation to users, the retrieved information including bid amounts associated with advertisements in the previously completed auctions; and

determining a number of the previously completed auctions in which an advertisement from the advertising campaign would have been selected, based at least in part on the retrieved information and the modified bid amounts associated with advertisements in the advertising campaign.

5. The method of claim 2, wherein determining the predicted performance of the advertising campaign during the interval comprises:

retrieving information describing previously completed auctions including advertisements associated with targeting criteria matching targeting criteria associated with one or more advertisements in the advertising campaign; and

determining a number of the previously completed auctions in which one or more advertisements from the advertising campaign would have been selected based at least in part on bid amounts associated with advertisements in the advertising campaign.

6. The method of claim 2, wherein determining the predicted performance of the advertising campaign during the interval comprises:

retrieving information describing previously completed auctions including advertisements associated with targeting criteria similar to targeting criteria associated with one or more advertisements in the advertising campaign; and

determining a number of the previously completed auctions in which one or more advertisements from the advertising campaign would have been selected based at least in part on bid amounts associated with advertisements in the advertising campaign.

7. The method of claim 2, wherein determining, by the computer, the one or more scaling filters based at least in part on the interval impression objective, the interval reach objective, the budget, and the performance of the advertising campaign comprises:

determining a ratio of the interval impression objective to the predicted number of impressions during the interval.

8. The method of claim 2, wherein determining, by the computer, the one or more scaling filters based at least in part on the interval impression objective, the interval reach objective, the budget, and the performance of the advertising campaign comprises:

determining a ratio of the interval reach objective to the predicted amount of reach during the interval.

9. The method of claim 2, wherein determining, by the computer, the one or more scaling filters based at least in part on the interval impression objective, the interval reach objective, the budget, and the performance of the advertising campaign comprises:

determining a reach scaling filter based at least in part on a ratio of the interval reach objective to the predicted amount of reach during the interval; and

determining an impression scaling filter based at least in part on a ratio of the interval reach objective to the predicted amount of reach during the interval.

10. The method of claim 1, wherein determining the interval impression objective comprises:

determining a target impression objective specifying a number of impressions at a completion of the interval;

determining a current number of impressions associated with the advertising campaign;

comparing the target impression objective to the current number of impressions; and

determining the interval impression objective based at least in part on the comparison.

11. The method of claim 1, wherein determining the interval reach objective comprises:

determining a target reach objective specifying an amount of reach at a completion of the interval;

determining a current reach of the advertising campaign;

comparing the target reach objective to the current reach; and

determining the interval reach objective based at least in part on the comparison.

12. The method of claim 1, wherein at least one scaling filter from the one or more scaling filters is a percentage of auctions in which advertisements from the advertising campaign will be included.

13. The method of claim 1, wherein at least one scaling filter from the one or more scaling filters is a percentage of auctions for opportunities to present advertisements to users not previously presented with at least one advertisement from the advertising campaign in which an advertisement from the advertising campaign will be included.

14. A computer program product comprising a non-transitory computer-readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:

receiving information for an advertising campaign including one or more advertisements for presentation to one or more users of a social networking system, the advertising campaign associated with a budget, an impression objective, and a reach objective;

determine an interval impression objective specifying a first portion of the impression objective to be completed in an interval of the advertising campaign based at least in part on a predicted performance of the advertising campaign during the interval, the interval representing a portion of the duration of the advertising campaign;

determine an interval reach objective specifying a first portion of the reach objective to be completed in the interval based at least in part on the predicted performance of the advertising campaign;

determine one or more scaling filters based at least in part on a combination of the interval impression objective, the interval reach objective, the budget, and the performance of the advertising campaign, the one or more scaling filters being usable to select of one or more advertisements of the advertising campaign for inclusion in advertisement auctions;

during a first interval;

identify a first plurality of opportunities to present advertisements to users of the social networking system,

determine whether to include one or more advertisements from the advertising campaign in auctions associated with the first plurality of identified opportunities based at least in part on the one or more scaling filters;

track a performance of the advertising campaign, the performance describing an impression count and a reach count from a start time of the advertising campaign, the impression count counting times an advertisement from the advertising campaign was presented to users of the social networking system and the reach count counting different users of the social networking system that were presented with an advertisement from the advertising campaign;

determine an updated interval impression objective specifying a second portion of the impression objective to be completed in a new interval of the advertising campaign based at least in part on the performance of the advertising campaign during the first interval;

determine an updated interval reach objective specifying a second portion of the reach objective to be completed in the new interval based at least in part on the performance of the advertising campaign during the first interval;

modify the one or more scaling filters based at least in part on a combination of the updated interval impression objective and the updated interval reach objective; and

during the new interval;

identify a second plurality of opportunities to present advertisements to users of the social networking system,

determine whether to include one or more advertisements from the advertising campaign in auctions associated with the second plurality of identified opportunities based at least in part on the one or more modified scaling filters.

15. The computer program product of claim 14, wherein the non-transitory computer-readable storage medium further has instructions encoded thereon that, when executed by the processor, cause the processor to:

determine the predicted performance of the advertising campaign during the time interval, the predicted performance describing a predicted number of impressions during the interval and a predicted amount of reach during the interval.

16. The computer program product of claim 15, wherein determine predicted the performance of the advertising campaign during the interval, the predicted performance describing the predicted number of impressions during the interval and the predicted amount of reach during the interval comprises:

retrieve information describing previously completed auctions selecting one or more advertisements for presentation to users, the retrieved information including bid amounts associated with advertisements in the previously completed auctions; and

determine a number of the previously completed auctions in which an advertisement from the advertising campaign would have been selected, based at least in part on the retrieved information and bid amounts associated with advertisements in the advertising campaign.

17. The computer program product of claim 15, wherein determine the predicted performance of the advertising campaign during the interval, the predicted performance describing the predicted number of impressions during the interval and the predicted amount of reach during the interval comprises:

determine a pacing factor based on an amount received from an advertiser associated with the advertising campaign at a start of the interval and the budget associated with the advertising campaign;

modify bid amounts associated with advertisements in the advertising campaign based at least in part on the pacing factor;

retrieve information describing previously completed auctions selecting one or more advertisements for presentation to users, the retrieved information including bid amounts associated with advertisements in the previously completed auctions; and

determine a number of the previously completed auctions in which an advertisement from the advertising campaign would have been selected, based at least in part on the retrieved information and the modified bid amounts associated with advertisements in the advertising campaign.

18. The computer program product of claim 15, wherein determine the predicted performance of the advertising campaign during the interval comprises:

retrieve information describing previously completed auctions including advertisements associated with targeting criteria matching targeting criteria associated with one or more advertisements in the advertising campaign; and

determine a number of the previously completed auctions in which one or more advertisements from the advertising campaign would have been selected based at least in part on bid amounts associated with advertisements in the advertising campaign.

19. The computer program product of claim 15, wherein determine the predicted performance of the advertising campaign during the interval comprises:

retrieve information describing previously completed auctions including advertisements associated with targeting criteria similar to targeting criteria associated with one or more advertisements in the advertising campaign; and

determine a number of the previously completed auctions in which one or more advertisements from the advertising campaign would have been selected based at least in part on bid amounts associated with advertisements in the advertising campaign.

20. The computer program product of claim 15, wherein determine the one or more scaling filters based at least in part on the interval impression objective, the interval reach objective, the budget, and the performance of the advertising campaign comprises:

determine a ratio of the interval impression objective to the predicted number of impressions during the interval.

21. The computer program product of claim 15, wherein determine the one or more scaling filters based at least in part on the interval impression objective, the interval reach objective, the budget, and the determined performance comprises:

determine a ratio of the interval reach objective to the predicted amount of reach during the interval.

22. The computer program product of claim 15, wherein determine the one or more scaling filters based at least in part on the interval impression objective, the interval reach objective, the budget, and the determined performance comprises:

determine a reach scaling filter based at least in part on a ratio of the interval reach objective to the predicted amount of reach during the interval; and

determine an impression scaling filter based at least in part on a ratio of the interval reach objective to the predicted amount of reach during the interval.

23. The computer program product of claim 14, wherein at least one scaling filter from the one or more scaling filters is a percentage of auctions in which advertisements from the advertising campaign will be included.

24. The computer program product of claim 14, wherein at least one scaling filter from the one or more scaling filters is a percentage of auctions for opportunities to present advertisements to users not previously presented with at least one advertisement from the advertising campaign in which an advertisement from the advertising campaign will be included.