Optimization of a multi-channel system using a feedback loop

1. 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, observed user actions with the content distributed to client devices over the multiple different online channels;

determining, by the one or more servers and based on the observed user actions received through the feedback loop, a predicted user action rate 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 the predicted user action rate and the same reference distribution amount specified by the provider of the content; and

distributing, by the one or more servers, the content using the adjusted selection value.

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

determining a difference between the predicted user action rate and the same reference distribution amount; and

adjusting the selection value in proportion to the difference between the predicted user action rate and the same reference distribution amount, including increasing the selection value in proportion to the difference when the predicted user action rate is less than the reference distribution amount and decreasing the selection value in proportion to the difference when the predicted user action rate is greater than the reference distribution amount.

3. The method of claim 2 , wherein adjusting the selection value comprises adjusting the selection value by a capped adjustment amount when the difference between the predicted user action rate and the same reference distribution amount is greater than a specified threshold difference.

4. The method of claim 1 , wherein determining the predicted user action rate comprises determining an average distribution amount for distributing the content over the multiple different online channels based on the observed user actions required for each distribution of the content over the multiple different online channels.

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

6. The method of claim 1 , 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 method 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 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, 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, observed user actions with the content distributed to client devices over the multiple different online channels;

determining, by the one or more servers and based on the observed user actions received through the feedback loop, a predicted user action rate 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 the predicted user action rate and the same reference distribution amount specified by the provider of the content; and

distributing, by the one or more servers, the content using the adjusted selection value.

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

determining a difference between the predicted user action rate and the same reference distribution amount; and

adjusting the selection value in proportion to the difference between the predicted user action rate and the same reference distribution amount, including increasing the selection value in proportion to the difference when the predicted user action rate is less than the reference distribution amount and decreasing the selection value in proportion to the difference when the predicted user action rate is greater than the reference distribution amount.

10. The system of claim 9 , wherein adjusting the selection value comprises adjusting the selection value by a capped adjustment amount when the difference between the predicted user action rate and the same reference distribution amount is greater than a specified threshold difference.

11. The system of claim 8 , wherein determining the predicted user action rate comprises determining an average distribution amount for distributing the content over the multiple different online channels based on the observed user actions required for each distribution of the content over the multiple different online channels.

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

13. The system of claim 8 , 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.

14. The system 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 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, observed user actions with the content distributed to client devices over the multiple different online channels;

determining, by the one or more servers and based on the observed user actions received through the feedback loop, a predicted user action rate 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 the predicted user action rate and the same reference distribution amount specified by the provider of the content; and

distributing, by the one or more servers, the content using the adjusted selection value.

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

determining a difference between the predicted user action rate and the same reference distribution amount; and

adjusting the selection value in proportion to the difference between the predicted user action rate and the same reference distribution amount, including increasing the selection value in proportion to the difference when the predicted user action rate is less than the reference distribution amount and decreasing the selection value in proportion to the difference when the predicted user action rate 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 predicted user action rate and the same reference distribution amount is greater than a specified threshold difference.

18. The computer program product of claim 15 , wherein determining the predicted user action rate comprises determining an average distribution amount for distributing the content over the multiple different online channels based on the observed user actions 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 user actions to a predicted user action rate for each distribution of the content during the given period of time, the total observed user actions 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.