Automated creative extension selection for content performance optimization

1. A method for optimizing content performance, the method comprising:

receiving, at a processing circuit, a request for third-party content for presentation on a client device, the request identifying a device type and a device location of the client device;

identifying, by the processing circuit, based on information in the request for third-party content, a plurality of potential click types that are available for inclusion in a content item selected for serving responsive to the request, wherein each click type of the plurality of potential click types define criteria for triggering an event that occurs in response to a user interaction with the content item that satisfies the criteria;

using a click type performance model and the device type and the device location of the client device to calculate, by the processing circuit, a predicted performance metric of the content item for each of the plurality of potential click types;

selecting, by the processing circuit, based on the predicted performance metric and the information in the request for third-party content, a click type of the plurality of potential click types, wherein the click type selected is different from a second click type selected in response to a second request for third-party content identifying a second device type and a second device location of a second client device;

comparing the predicted performance metric with a threshold value;

wherein selecting one of the plurality of potential click types comprises:

selecting a first click type of the plurality of potential click types if the predicted performance metric is less than the threshold value; and

selecting a second click type of the plurality of potential click types if the predicted performance metric is not less than the threshold value;

generating, by the processing circuit, responsive to the request, the content item to include the selected click type, the generated content item configured to trigger the event responsive to a user interaction that satisfies criteria defined by the selected click type; and

serving the generated content item for presentation on the client device.

2. The method of claim 1 , further comprising:

collecting and storing event data describing user actions with respect to content items having each of the plurality of potential click types; and

using the event data as feedback for training the click type performance model.

3. The method of claim 1 , wherein the criteria defined by the plurality of potential click types comprise different types of user interactions with the content item.

4. The method of claim 1 , wherein each of the plurality of potential click types defines different criteria for calculating the predicted performance metric.

5. The method of claim 1 , wherein selecting the click type of the plurality of potential click types comprises selecting a button click type, the method further comprising:

defining the criteria for triggering the event as a user interaction with a first portion of the content item excluding user interactions with a second portion of the content item separate from the first portion; and

rendering a clickable button that occupies only the first portion of the content item.

6. The method of claim 1 , wherein selecting the click type of the plurality of potential click types comprises selecting a whole content item click type, the method further comprising:

defining the criteria for triggering the event as a user interaction with any portion of the content item; and

rendering an entire display area of the content item as a clickable element.

7. The method of claim 1 , wherein selecting the click type of the plurality of potential click types comprises selecting a confirmation click type, the method further comprising:

displaying a confirmation prompt in response to a first user interaction with the content item; and

defining the criteria for triggering the event as a second user interaction with the content item occurring after the first user interaction and while the confirmation prompt is displayed.

8. The method of claim 1 , wherein selecting the click type of the plurality of potential click types comprises selecting the click type associated with an extremum of the predicted performance metrics for the plurality of potential click types.

9. The method of claim 1 , further comprising:

comparing the predicted performance metric with a threshold value, wherein selecting one of the plurality of potential click types comprises:

selecting a first click type of the plurality of potential click types if the predicted performance metric is less than the threshold value, and

selecting a second click type of the plurality of potential click types if the predicted performance metric is not less than the threshold value.

10. The method of claim 1 , wherein the request further comprises a landing page identifier of a landing page into which the content item will be inserted, and wherein the predicted performance metric of the content item for each of the plurality of potential click types is calculated further based on the landing page identifier.

11. A system for optimizing content performance, the system comprising: a processing circuit having a processor and memory, wherein the processing circuit is configured to:

receive a request for third-party content for presentation on a client device, the request identifying a device type and a device location of the client device;

identify, based on information in the request for third-party content, a plurality of potential click types that are available for inclusion in a content item selected for serving responsive to the request, wherein each click type of the plurality of potential click types defines criteria for triggering an event that occurs in response to a user interaction with the content item that satisfies the criteria;

use a click type performance model and the device type and the device location of the client device to calculate a predicted performance metric of the content item for each of the plurality of potential click types;

select, based on the predicted performance metric and the information in the request for third-party content, a click type of the plurality of potential click types, wherein the click type selected is different from a second click type selected in response to a second request for third-party content identifying a second device type and a second device location of a second device;

compare the predicted performance metric with a threshold value;

wherein selecting the click type of the plurality of potential click types comprises:

selecting a first click type of the plurality of potential click types if the predicted performance metric is less than the threshold value; and

selecting a second click type of the plurality of potential click types if the predicted performance metric is not less than the threshold value

generate, responsive to the request, the content item to include the selected click type in response to the request, the generated content item configured to trigger the event responsive to a user interaction that satisfies criteria defined by the selected click type; and

serve the generated content item for presentation on the client device.

12. The system of claim 11 , wherein the processing circuit is configured to:

collect and store event data describing user actions with respect to content items having each of the plurality of potential click types; and

use the event data as feedback for training the click type performance model.

13. The system of claim 11 , wherein the criteria defined by the plurality of potential click types comprise different types of user interactions with the content item.

14. The system of claim 11 , wherein each of the plurality of potential click types defines different criteria for calculating the predicted performance metric.

15. The system of claim 11 , wherein selecting the click type of the plurality of potential click types comprises selecting a button click type, wherein the processing circuit is configured to:

define the criteria for triggering the event as a user interaction with a first portion of the content item excluding user interactions with a second portion of the content item separate from the first portion; and

render a clickable button that occupies only the first portion of the content item.

16. The system of claim 11 , wherein selecting the click type of the plurality of potential click types comprises selecting a whole content item click type, wherein the processing circuit is configured to:

define the criteria for triggering the event as a user interaction with any portion of the content item; and

render an entire display area of the content item as a clickable element.

17. The system of claim 11 , wherein selecting the click type of the plurality of potential click types comprises selecting a confirmation click type, wherein the processing circuit is configured to:

configure the content item to cause a confirmation prompt to be displayed in response to a first user interaction with the content item; and

define the criteria for triggering the event as a second user interaction with the content item occurring after the first user interaction and while the confirmation prompt is displayed.

18. The system of claim 11 , wherein selecting the click type of the plurality of potential click types comprises selecting the click type associated with an extremum of the predicted performance metrics for the plurality of potential click types.

19. The system of claim 11 , wherein the processing circuit is configured to:

compare the predicted performance metric with a threshold value, wherein selecting the click type of the plurality of potential click types comprises:

selecting a first click type of the plurality of potential click types if the predicted performance metric is less than the threshold value, and

selecting a second click type of the plurality of potential click types if the predicted performance metric is not less than the threshold value.

20. A non-transitory computer storage medium comprising computer program instructions stored thereon, the computer program instructions when executed by one or more processors cause the one or more processors to:

receive a request for third-party content for presentation on a client device, the request identifying a device type and a device location of the client device;

identify, based on information in the request for third-party content, a plurality of potential click types that are available for inclusion in a content item selected for serving responsive to the request, wherein each click type of the plurality of potential click types defines criteria for triggering an event that occurs in response to a user interaction with the content item that satisfies the criteria;

use a click type performance model and the device type and the device location of the client device to calculate a predicted performance metric of the content item for each of the plurality of potential click types;

select, based on the predicted performance metric and the information in the request for third-party content, a click type of the plurality of potential click types, wherein the click type selected is different from a second click type selected in response to a second request for third-party content identifying a second device type and a second device location of a second device;

compare the predicted performance metric with a threshold value;

wherein selecting the click type of the plurality of potential click types comprises:

selecting a first click type of the plurality of potential click types if the predicted performance metric is less than the threshold value; and

selecting a second click type of the plurality of potential click types if the predicted performance metric is not less than the threshold value

generate, responsive to the request, the content item to include the selected click type in response to the request, the generated content item configured to trigger the event responsive to a user interaction that satisfies criteria defined by the selected click type; and

serve the generated content item for presentation on the client device.