Optimized digital component analysis system

1. A method performed by data processing apparatus, the method comprising:

receiving, from a client device, a component request specifying a maximum number of digital components that are capable of being presented on a particular electronic document being rendered at the client device;

obtaining a current eligibility value for a given digital component;

obtaining historical eligibility value data for the given digital component;

determining a maximum interaction increase factor for the given digital component based on a largest level of increase in user interactions provided by formatting available to be applied to the given digital component;

determining a ranking score for the given digital component based on the maximum interaction increase factor of formatting available to be applied to the given digital component, the current eligibility value, and the historical eligibility value data;

ranking the given digital component among other available digital components based on a comparison of the determined ranking score for the given digital component and ranking scores of the other available digital components;

determining, based on the ranking, that the given digital component rank is included the maximum number of highest ranked digital components;

selecting the given digital component for distribution in response to the component request based on the ranking score of the given digital component being included in the maximum number of highest ranked digital components; and

transmitting the given digital component to the client device identified in the component request based on the selection of the given digital component for distribution, wherein determining the maximum interaction increase factor comprises:

evaluating, for each available formatting, an increase in user interactions provided by each available formatting;

identifying, based on the evaluating, the available formatting that provides a largest increase in user interactions relative to a level of user interactions attributed to the given digital component without any formatting applied; and

determining the maximum interaction increase factor based on an interaction rate provided by the available formatting that provides a largest increase in user interactions.

2. The method of claim 1 , further comprising:

determining a cumulative distribution function based on the historical eligibility value data; and

determining a probability density function as a derivative of the cumulative distribution function.

3. The method of claim 1 , wherein determining the maximum interaction increase factor based on an interaction rate provided by the available formatting that provides a largest increase in user interactions comprises determining a ratio between an interaction rate for the given digital component when formatted according to the available formatting that provides the highest interaction rate for the given digital component and the interaction rate for the given digital component when none of the available formatting is applied to the given digital component.

4. The method of claim 3 , wherein determining the ranking score comprises determining a product of the maximum interaction increase factor and a value provided by the cumulative distribution function at a location corresponding to the current eligibility value of the given digital component.

5. The method of claim 1 , further comprising formatting the given digital component according to the available formatting that provides the largest increase in user interactions.

6. The method of claim 5 , wherein formatting the given digital component according to the available formatting that provides the largest increase in user interactions comprises dynamically modifying a visual appearance or code of the digital component prior to transmitting the digital component to the client device responsive to the component request.

7. A non-transitory computer readable medium storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:

receiving, from a client device, a component request specifying a maximum number of digital components that are capable of being presented on a particular electronic document being rendered at the client device;

obtaining a current eligibility value for a given digital component;

obtaining historical eligibility value data for the given digital component;

determining a maximum interaction increase factor for the given digital component based on a largest level of increase in user interactions provided by formatting available to be applied to the given digital component;

determining a ranking score for the given digital component based on the maximum interaction increase factor of formatting available to be applied to the given digital component, the current eligibility value, and the historical eligibility value data;

ranking the given digital component among other available digital components based on a comparison of the determined ranking score for the given digital component and ranking scores of the other available digital components;

determining, based on the ranking, that the given digital component rank is included the maximum number of highest ranked digital components;

selecting the given digital component for distribution in response to the component request based on the ranking score of the given digital component being included in the maximum number of highest ranked digital components; and

transmitting the given digital component to the client device identified in the component request based on the selection of the given digital component for distribution, wherein determining the maximum interaction increase factor comprises:

evaluating, for each available formatting, an increase in user interactions provided by each available formatting;

identifying, based on the evaluating, the available formatting that provides a largest increase in user interactions relative to a level of user interactions attributed to the given digital component without any formatting applied; and

determining the maximum interaction increase factor based on an interaction rate provided by the available formatting that provides a largest increase in user interactions.

8. The non-transitory computer readable medium of claim 7 , wherein the instructions cause the one or more computing devices to perform operations further comprising:

determining a cumulative distribution function based on the historical eligibility value data; and

determining a probability density function as a derivative of the cumulative distribution function.

9. The non-transitory computer readable medium of claim 7 , wherein determining the maximum interaction increase factor based on an interaction rate provided by the available formatting that provides a largest increase in user interactions comprises determining a ratio between an interaction rate for the given digital component when formatted according to the available formatting that provides the highest interaction rate for the given digital component and the interaction rate for the given digital component when none of the available formatting is applied to the given digital component.

10. The non-transitory computer readable medium of claim 9 , wherein determining the ranking score comprises determining a product of the maximum interaction increase factor and a value provided by the cumulative distribution function at a location corresponding to the current eligibility value of the given digital component.

11. The non-transitory computer readable medium of claim 9 , wherein the instructions cause the one or more computing devices to perform operations further comprising formatting the given digital component according to the available formatting that provides the largest increase in user interactions.

12. The non-transitory computer readable medium of claim 11 , wherein formatting the given digital component according to the available formatting that provides the largest increase in user interactions comprises dynamically modifying a visual appearance or code of the digital component prior to transmitting the digital component to the client device responsive to the component request.

13. A system comprising:

a data storage device storing machine executable instructions; and

one or more distributed computing devices that interact with the data storage device and execute the instructions, wherein execution of the instructions causes the one or more distributed computing devices to perform operations comprising:

receiving, from a client device, a component request specifying a maximum number of digital components that are capable of being presented on a particular electronic document being rendered at the client device;

obtaining a current eligibility value for a given digital component;

obtaining historical eligibility value data for the given digital component;

determining a maximum interaction increase factor for the given digital component based on a largest level of increase in user interactions provided by formatting available to be applied to the given digital component;

determining a ranking score for the given digital component based on the maximum interaction increase factor of formatting available to be applied to the given digital component, the current eligibility value, and the historical eligibility value data;

ranking the given digital component among other available digital components based on a comparison of the determined ranking score for the given digital component and ranking scores of the other available digital components;

determining, based on the ranking, that the given digital component rank is included the maximum number of highest ranked digital components;

selecting the given digital component for distribution in response to the component request based on the ranking score of the given digital component being included in the maximum number of highest ranked digital components; and

transmitting the given digital component to the client device identified in the component request based on the selection of the given digital component for distribution, wherein determining the maximum interaction increase factor comprises:

evaluating, for each available formatting, an increase in user interactions provided by each available formatting;

identifying, based on the evaluating, the available formatting that provides a largest increase in user interactions relative to a level of user interactions attributed to the given digital component without any formatting applied; and

determining the maximum interaction increase factor based on an interaction rate provided by the available formatting that provides a largest increase in user interactions.

14. The system of claim 13 , wherein the instructions cause the one or more computing devices to perform operations further comprising:

determining a cumulative distribution function based on the historical eligibility value data; and

determining a probability density function as a derivative of the cumulative distribution function.

15. The system of claim 13 , wherein determining the maximum interaction increase factor based on an interaction rate provided by the available formatting that provides a largest increase in user interactions comprises determining a ratio between an interaction rate for the given digital component when formatted according to the available formatting that provides the highest interaction rate for the given digital component and the interaction rate for the given digital component when none of the available formatting is applied to the given digital component.

16. The system of claim 15 , wherein determining the ranking score comprises determining a product of the maximum interaction increase factor and a value provided by the cumulative distribution function at a location corresponding to the current eligibility value of the given digital component.

17. The system of claim 15 , wherein the instructions cause the one or more computing devices to perform operations further comprising formatting the given digital component according to the available formatting that provides the largest increase in user interactions.