Optimization of a multi-channel system using a feedback loop

1. A system comprising:

a third-party content corpus database that stores information for various content that are available to be distributed to client devices; and

a distributed computing environment, including multiple computing devices and a feedback loop wherein the distributed computing environment interacts with the third-party content corpus database and performs operations comprising:

distributing content over multiple different online channels using a same reference distribution amount specified by a provider of the content for distribution over the multiple different online channels, wherein the feedback loop is configured to obtain feedback about the distributions and adjust a transmission of content over the multiple different online channels by adjusting a selection value used to distribute content over the multiple different online channels;

receiving, through the feedback loop and for multiple different distributions of the content over the multiple different online channels, an observed distribution amount required for distribution of the content to client devices over the multiple different online channels;

determining, based on the observed distribution amount received through the feedback loop, a realized distribution amount for the multiple different distributions across the multiple different online channels;

adjusting the selection value for the multiple different online channels based on a difference between the realized distribution amount and the same reference distribution amount specified by the provider of the content; and

distributing the content over the multiple different online channels using the adjusted maximum selection value.

2. The system of claim 1 , wherein adjusting the selection value comprises:

determining a difference between the realized distribution amount and the reference distribution amount; and

adjusting the selection value in proportion to the difference between the realized distribution amount and the reference distribution amount, including increasing the selection value in proportion to the difference when the realized distribution amount is less than the reference distribution amount and decreasing the selection value in proportion to the difference when the realized distribution amount is greater than the reference distribution amount.

3. The system of claim 2 , wherein adjusting the selection value comprises adjusting the selection value by a capped adjustment amount when the difference between the realized distribution amount and the reference distribution amount is greater than a specified threshold difference.

4. The system of claim 1 , wherein determining the realized distribution amount comprises determining an average distribution amount for distributing the content over the multiple different online channels based on the observed distribution amount required for each distribution of the content over the multiple different online channels.

5. The system of claim 4 , wherein determining the average distribution amount comprises determining, for a given period of time, a ratio of a total observed distribution amount to a predicted user action rate for each distribution of the content during the given period of time, the total observed distribution amount being a total amount required to distribute the content over the given period of time.

6. The system of claim 1 , wherein the distributed computing environment performs operations further comprising generating an initial instance of the selection value based on the reference distribution amount and an initialization factor that causes the initial instance of the selection value to be greater than the reference distribution amount.

7. The system of claim 1 , wherein distributing the content over the multiple different online channels comprises distributing the content over each of a web page and a streaming media channel.

8. A method, comprising:

distributing, by one or more servers in a distributed computing environment, content over multiple different online channels using a same reference distribution amount specified by a provider of the content for distribution over the multiple different online channels, wherein a feedback loop is configured to obtain feedback about the distributions and adjust a transmission of content over the multiple different online channels by adjusting a selection value used to distribute content over the multiple different online channels;

receiving, through a feedback loop and for multiple different distributions of the content over the multiple different online channels, an observed distribution amount required for distribution of the content to client devices over the multiple different online channels;

determining, by the one or more servers and based on the observed distribution amount received through the feedback loop, a realized distribution amount for the multiple different distributions across the multiple different online channels;

adjusting, by the one or more servers, the selection value for the multiple different online channels based on a difference between the realized distribution amount and the same reference distribution amount specified by the provider of the content; and

distributing, by the one or more servers, the content over the multiple different online channels using the adjusted maximum selection value.

9. The method of claim 8 , wherein adjusting the selection value comprises:

determining a difference between the realized distribution amount and the reference distribution amount; and

adjusting the selection value in proportion to the difference between the realized distribution amount and the reference distribution amount, including increasing the selection value in proportion to the difference when the realized distribution amount is less than the reference distribution amount and decreasing the maximum selection value in proportion to the difference when the realized distribution amount is greater than the reference distribution amount.

10. The method of claim 9 , wherein adjusting the selection value comprises adjusting the selection value by a capped adjustment amount when the difference between the realized distribution amount and the reference distribution amount is greater than a specified threshold difference.

11. The method of claim 8 , wherein determining the realized distribution amount comprises determining an average distribution amount for distributing the content over the multiple different online channels based on the observed distribution amount required for each distribution of the content over the multiple different online channels.

12. The method of claim 11 , wherein determining the average distribution amount comprises determining, for a given period of time, a ratio of a total observed distribution amount to a predicted user action rate for each distribution of the content during the given period of time, the total observed distribution amount being a total amount required to distribute the content over the given period of time.

13. The method of claim 8 , further comprising generating an initial instance of the selection value based on the reference distribution amount and an initialization factor that causes the initial instance of the selection value to be greater than the reference distribution amount.

14. The method of claim 8 , wherein distributing the content over the multiple different online channels comprises distributing the content over each of a web page and a streaming media channel.

15. A computer program product embodied in a non-transitory computer-readable medium including instructions, that when executed, cause one or more processors to perform operations comprising:

distributing, by one or more servers, content over multiple different online channels using a same reference distribution amount specified by a provider of the content for distribution over the multiple different online channels, wherein a feedback loop is configured to obtain feedback about the distributions and adjust a transmission of content over the multiple different online channels by adjusting a selection value used to distribute content over the multiple different online channels;

receiving, through a feedback loop and for multiple different distributions of the content over the multiple different online channels, an observed distribution amount required for distribution of the content to client devices over the multiple different online channels;

determining, by the one or more servers and based on the observed distribution amount received through the feedback loop, a realized distribution amount for the multiple different distributions across the multiple different online channels;

adjusting, by the one or more servers, the selection value for the multiple different online channels based on a difference between the realized distribution amount and the same reference distribution amount specified by the provider of the content; and

distributing, by the one or more servers, the content over the multiple different online channels using the adjusted maximum selection value.

16. The computer program product of claim 15 , wherein adjusting the selection value comprises:

determining a difference between the realized distribution amount and the reference distribution amount; and

adjusting the selection value in proportion to the difference between the realized distribution amount and the reference distribution amount, including increasing the selection value in proportion to the difference when the realized distribution amount is less than the reference distribution amount and decreasing the selection value in proportion to the difference when the realized distribution amount is greater than the reference distribution amount.

17. The computer program product of claim 16 , wherein adjusting the selection value comprises adjusting the selection value by a capped adjustment amount when the difference between the realized distribution amount and the reference distribution amount is greater than a specified threshold difference.

18. The computer program product of claim 15 , wherein determining the realized distribution amount comprises determining an average distribution amount for distributing the content over the multiple different online channels based on the observed distribution amount required for each distribution of the content over the multiple different online channels.

19. The computer program product of claim 18 , wherein determining the average distribution amount comprises determining, for a given period of time, a ratio of a total observed distribution amount to a predicted user action rate for each distribution of the content during the given period of time, the total observed distribution amount being a total amount required to distribute the content over the given period of time.

20. The computer program product of claim 15 , the operations further comprising generating an initial instance of the selection value based on the reference distribution amount and an initialization factor that causes the initial instance of the selection value to be greater than the reference distribution amount.