SYSTEMS AND METHODS FOR BLENDING CONTENT ITEMS

1 . A computer-implemented method comprising:

determining, by a social networking system, respective rates at which one or more types of content items were presented to users of the social networking system over a period of time, wherein each content item is associated with a respective bid, and wherein content items are presented through impression opportunities based at least in part on a real-time bidding auction;

determining, by the social networking system, that the respective rates measured over the period of time are inconsistent with a specified mix of the types of content items to be presented; and

causing, by the social networking system, the respective bids associated with content items of at least a first type to be adjusted by a corresponding bid weight, wherein the bids are adjusted to enforce the specified mix.

2 . The computer-implemented method of claim 1 , wherein the mix specifies a ratio of content items of the first type to content items of a second type.

3 . The computer-implemented method of claim 1 , wherein the mix specifies a ratio of at least content items of the first type, to content items of a second type, and to content items of a third type.

4 . The computer-implemented method of claim 1 , the method further comprising:

determining, by the social networking system, the respective bid weight for content items of the first type based at least in part on the respective rates measured over the period of time.

5 . The computer-implemented method of claim 1 , the method further comprising:

determining, by the social networking system, respective rates at which the one or more types of content items were presented to users of the social networking system over a subsequent period of time;

determining, by the social networking system, that the respective rates measured over the subsequent period of time are inconsistent with the specified mix;

determining, by the social networking system, a new bid weight for content items of the first type based at least in part on the respective rates measured over the subsequent period of time; and

causing, by the social networking system, the respective bids associated with content items of the first type to be adjusted by the new bid weight.

6 . The computer-implemented method of claim 1 , wherein determining that the respective rates measured over the period of time are inconsistent with the specified mix further comprises:

determining, by the social networking system, that a difference between the respective rates and the specified mix exceeds a tolerance value.

7 . The computer-implemented method of claim 1 , the method further comprising:

causing, by the social networking system, the respective bids associated with content items of at least a second type to be adjusted by a bid weight corresponding to the second type, wherein the bids are adjusted to enforce the specified mix.

8 . The computer-implemented method of claim 1 , wherein causing the respective bids associated with content items of at least the first type to be adjusted further comprises:

causing, by the social networking system, the respective bid associated with each content item of the first type to be increased based at least in part on the bid weight.

9 . The computer-implemented method of claim 1 , wherein causing the respective bids associated with content items of at least the first type to be adjusted further comprises:

causing, by the social networking system, the respective bid associated with each content item of the first type to be decreased based at least in part on the bid weight.

10 . The computer-implemented method of claim 1 , wherein the types of content items include at least one of advertisements or various entities accessible through the social networking system.

11 . A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform:

determining respective rates at which one or more types of content items were presented to users of the social networking system over a period of time, wherein each content item is associated with a respective bid, and wherein content items are presented through impression opportunities based at least in part on a real-time bidding auction;

determining that the respective rates measured over the period of time are inconsistent with a specified mix of the types of content items to be presented; and

causing the respective bids associated with content items of at least a first type to be adjusted by a corresponding bid weight, wherein the bids are adjusted to enforce the specified mix.

12 . The system of claim 11 , wherein the mix specifies a ratio of content items of the first type to content items of a second type.

13 . The system of claim 11 , wherein the mix specifies a ratio of at least content items of the first type, to content items of a second type, and to content items of a third type.

14 . The system of claim 11 , wherein the system further performs:

determining the respective bid weight for content items of the first type based at least in part on the respective rates measured over the period of time.

15 . The system of claim 11 , wherein the system further performs:

determining respective rates at which the one or more types of content items were presented to users of the social networking system over a subsequent period of time;

determining that the respective rates measured over the subsequent period of time are inconsistent with the specified mix;

determining a new bid weight for content items of the first type based at least in part on the respective rates measured over the subsequent period of time; and

causing the respective bids associated with content items of the first type to be adjusted by the new bid weight.

16 . A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

determining respective rates at which one or more types of content items were presented to users of the social networking system over a period of time, wherein each content item is associated with a respective bid, and wherein content items are presented through impression opportunities based at least in part on a real-time bidding auction;

determining that the respective rates measured over the period of time are inconsistent with a specified mix of the types of content items to be presented; and

causing the respective bids associated with content items of at least a first type to be adjusted by a corresponding bid weight, wherein the bids are adjusted to enforce the specified mix.

17 . The non-transitory computer-readable storage medium of claim 16 , wherein the mix specifies a ratio of content items of the first type to content items of a second type.

18 . The non-transitory computer-readable storage medium of claim 16 , wherein the mix specifies a ratio of at least content items of the first type, to content items of a second type, and to content items of a third type.

19 . The non-transitory computer-readable storage medium of claim 16 , wherein the computing system further performs:

determining the respective bid weight for content items of the first type based at least in part on the respective rates measured over the period of time.

20 . The non-transitory computer-readable storage medium of claim 16 , wherein the computing system further performs:

determining respective rates at which the one or more types of content items were presented to users of the social networking system over a subsequent period of time;

determining that the respective rates measured over the subsequent period of time are inconsistent with the specified mix;

determining a new bid weight for content items of the first type based at least in part on the respective rates measured over the subsequent period of time; and

causing the respective bids associated with content items of the first type to be adjusted by the new bid weight.