Predicting the Performance of an Advertising Campaign

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 one or more targeting criteria;

retrieving information describing previously completed advertisement auctions that each selected an advertisement for presentation to a user of the social networking system associated with characteristics satisfying one or more of the targeting criteria, the retrieved information including bid amounts of advertisements selected in the previously completed advertisement auctions and a charged price associated with each advertisement selected in a previously completed advertisement auction; and

for a plurality of bid amounts,

selecting a bid amount from the plurality of bid amounts;

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

storing the selected bid amount in association with the number of previously completed advertisements in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected.

2 . The method of claim 1 , further comprising:

for the plurality of bid amounts,

determining a price charged in each of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected based at least in part on the retrieved information;

determining a number of distinct users to whom previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected, based at least in part on the retrieved information and the selected bid amount; and

storing the price charged in each previously completed advertisement auctions in which the advertisement from the advertising campaign with the selected bid amount would have been selected, and the number of distinct users.

3 . The method of claim 2 , wherein the received information for the advertising campaign includes a budget associated with the advertising campaign.

4 . The method of claim 3 , further comprising:

determining a maximum number of distinct users for which one or more advertisement from the advertising campaign would have been selected based at least in part on the determined prices associated with each bid amount from the plurality of bid amounts, the number of distinct users to whom previously completed advertisement auctions in which the advertisement from the advertising campaign associated with each bid amount would have been selected, and the budget associated with the advertising campaign.

5 . The method of claim 4 , wherein determining the maximum number of distinct users comprises:

identifying a bid amount from the plurality of bid amounts associated with a maximum value for a total amount charged that does exceed the budget, the total amount charged based at least in part on the determined price charged associated with identified bid amount and the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected; and

determining the maximum number of distinct users as the number of distinct users to whom previously completed advertisement auctions in which one or more advertisements from the advertising campaign associated with identified bid amount would have been selected.

6 . The method of claim 2 , wherein the received information for the advertising campaign includes a reach objective specifying a number of distinct users to be presented with one or more advertisements from the advertising campaign.

7 . The method of claim 6 , further comprising:

determining a budget for the advertising campaign based at least in part on the determined prices charged associated with each bid amount from the plurality of bid amounts, the number of distinct users to whom previously completed advertisement auctions in which the advertisement from the advertising campaign associated with each bid amount would have been selected, the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected, and the reach objective.

8 . The method of claim 7 , wherein determining the budget for the advertising campaign comprises:

identifying a bid amount from the plurality of bid amounts associated a number of distinct users to whom previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the bid amount from the plurality of bid amounts would have been selected that is within a threshold amount of the reach objective; and

determining the budget based at least in part on the determined price charged associated with identified bid amount and the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected.

9 . The method of claim 8 , wherein determining the budget based at least in part on the determined price charged associated with the identified bid amount and the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected comprises:

determining a product of the price charged associated with the identified bid amount and the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected as the budget.

10 . The method of claim 2 , wherein determining the number of the previously completed advertisement auctions in which an advertisement from the advertising campaign associated with the selected bid amount would have been selected, based at least in part on the retrieved information and the selected bid amount comprises:

retrieving a context scalar associated with each of the previously completed advertisement auctions from the retrieved information, the context scalar describing a context in which an advertisement selected by a previously completed advertisement auction was presented;

modifying bid amounts associated with each of the previously completed advertisement auctions based at least in part on the retrieved context scalars; and

determining a number of the previously completed advertisement auctions in which the selected bid amount is greater than a modified bid amount associated with the previously completed advertisement auction.

11 . The method of claim 2 , wherein the received information for the advertising campaign further includes a frequency cap, and wherein determining the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected comprises:

identifying users associated with each of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected;

determining a number of the previously completed advertisement auctions in which the advertisement form the advertising campaign associated with the selected bid amount would have been selected associated with each identified user; and

associating a number of previously completed advertisement auctions in which the advertisement with the advertising campaign would have been selected equal to the frequency cap with a user associated with a number of previously completed advertisement auctions in which the advertisement with the advertising campaign that exceeds the frequency cap.

12 . The method of claim 2 , wherein determining the price charged in each of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected based at least in part on the retrieved information comprises:

determining an average price charged based on prices charged in each in each of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected.

13 . 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:

receive 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 one or more targeting criteria;

retrieve information describing previously completed advertisement auctions that each selected an advertisement for presentation to a user of the social networking system associated with characteristics satisfying one or more of the targeting criteria, the retrieved information including bid amounts of advertisements selected in the previously completed advertisement auctions and a charged price associated with each advertisement selected in a previously completed advertisement auction; and

for a plurality of bid amounts,

select a bid amount from the plurality of bid amounts;

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

determine a price charged in each of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected based at least in part on the retrieved information; and

determine a number of distinct users to whom previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected, based at least in part on the retrieved information and the selected bid amount; and

store the selected bid amount in association with the number of previously completed advertisements in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected, the price charged in each previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected, and the number of distinct users.

14 . The computer program product of claim 13 , wherein the non-transitory computer readable storage medium further has instructions encoded thereon that, when executed by the processor, cause the processor to:

for the plurality of bid amounts,

determine a price charged in each of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected based at least in part on the retrieved information; and

determine a number of distinct users to whom previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected, based at least in part on the retrieved information and the selected bid amount; and

store the price charged in each previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected, and the number of distinct users.

15 . The computer program product of claim 14 , wherein the received information for the advertising campaign includes a budget associated with the advertising campaign.

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

determine a maximum number of distinct users for which one or more advertisement from the advertising campaign would have been selected based at least in part on the determined prices associated with each bid amount from the plurality of bid amounts, the number of distinct users to whom previously completed advertisement auctions in which the advertisement from the advertising campaign associated with each bid amount would have been selected, and the budget associated with the advertising campaign.

17 . The computer program product of claim 16 , wherein determine the maximum number of distinct users comprises:

identify a bid amount from the plurality of bid amounts associated with a maximum value for a total amount charged that does exceed the budget, the total amount charged based at least in part on the determined price charged associated with identified bid amount and the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected; and

determine the maximum number of distinct users as the number of distinct users to whom previously completed advertisement auctions in which one or more advertisements from the advertising campaign associated with identified bid amount would have been selected.

18 . The computer program product of claim 14 , wherein the received information for the advertising campaign includes a reach objective specifying a number of distinct users to be presented with one or more advertisements from the advertising campaign.

19 . The computer program product of claim 18 , wherein the non-transitory computer readable storage medium further has instructions encoded thereon that, when executed by the processor, cause the prossor to:

determine a budget for the advertising campaign based at least in part on the determined prices charged associated with each bid amount from the plurality of bid amounts, the number of distinct users to whom previously completed advertisement auctions in which the advertisement from the advertising campaign associated with each bid amount would have been selected, the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected, and the reach objective.

20 . The computer program product of claim 19 , wherein determine the budget for the advertising campaign comprises:

identify a bid amount from the plurality of bid amounts associated a number of distinct users to whom previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the bid amount from the plurality of bid amounts would have been selected that is within a threshold amount of the reach objective; and

determine the budget based at least in part on the determined price charged associated with identified bid amount and the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected.

21 . The computer program product of claim 20 , wherein determine the budget based at least in part on the determined price charged associated with the identified bid amount and the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected comprises:

determine a product of the price charged associated with the identified bid amount and the number of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the identified bid amount would have been selected as the budget.

22 . The computer program product of claim 14 , wherein determine the price charged in each of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected based at least in part on the retrieved information comprises:

determine an average price charged based on prices charged in each in each of the previously completed advertisement auctions in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected.

23 . A system comprising:

a processor; and

a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by the processor, cause the processor to:

receive 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 one or more targeting criteria;

retrieve information describing previously completed advertisement auctions that each selected an advertisement for presentation to a user of the social networking system associated with characteristics satisfying one or more of the targeting criteria, the retrieved information including bid amounts of advertisements selected in the previously completed advertisement auctions and a charged price associated with each advertisement selected in a previously completed advertisement auction; and

for a plurality of bid amounts,

select a bid amount from the plurality of bid amounts;

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

store the selected bid amount in association with the number of previously completed advertisements in which the advertisement from the advertising campaign associated with the selected bid amount would have been selected.