Content item selection for goal achievement

1. A method, comprising:

executing, on a processor of a computing device, instructions that cause the computing device to perform operations, the operations comprising:

identifying a goal of a user;

utilizing a machine learning model to evaluate the goal, user information, and a set of content items to generate predictions for the content items of how likely each content item will be a causation factor of the user making progress towards the goal in response to the user being provided with each content item, wherein the predictions for the content items comprise (i) a first predicted likelihood that viewing a first content item will cause the user to make progress towards the goal and (ii) a second predicted likelihood that viewing a second content item will cause the user to make progress towards the goal,

the machine learning model trained based upon data indicative of one or more activities of at least one of the user or one or more other users;

selecting a target content item, based upon the predictions generated utilizing the machine learning model, from the set of content items based upon the target content item having a predicted likelihood of being the causation factor above a threshold;

providing, via a network connection, the target content item through a registered media channel accessible through a device of the user;

tracking, via one or more network connections, feedback comprising data indicative of one or more further activities indicative of progress of the user towards the goal after providing the target content item to the user;

training the machine learning model, based upon the tracked feedback comprising the data indicative of the one or more further activities indicative of progress, to generate a trained machine learning model;

utilizing the trained machine learning model to generate second predictions; and

providing one or more content items based upon the second predictions generated utilizing the trained machine learning model.

2. The method of claim 1 , comprising:

statistically filtering the set of content items to identify content items that correlate to goal progress for groups of users.

3. The method of claim 1 , comprising:

performing A/B testing for a content item by tracking whether a first set of users provided with the content item made progress towards the goal and whether a second set of users not provided with the content item made progress towards the goal.

4. The method of claim 1 , wherein the machine learning-model comprises a function with an input of an item input, a user input, and a goal input, and wherein the function outputs an increase in probability that the user will make progress towards the goal if provided with the content item based upon a difference between a probability the user makes progress towards the goal if provided with the content item and a probability the user makes progress towards the goal if the user is not provided with the content item.

5. The method of claim 1 , wherein the machine learning-model maps a combination of user, item, and goal to a difference in probability that a target user will make progress towards a target goal if a content item is provided to the target user.

6. The method of claim 1 , comprising:

tracking progress of users towards goals based upon content items provided to the users.

7. The method of claim 6 , comprising:

generating historical data for each user relating to content items provided to each user and goal progress data.

8. The method of claim 7 , comprising:

clustering similar users into clusters;

identifying a cluster to which the user belongs; and

utilizing an aggregate of historical data of users within the cluster as an input to the machine learning model for selecting the target content item for the user.

9. The method of claim 1 , wherein the target content item comprises a recommendation to take a break from content consumption.

10. The method of claim 1 , comprising:

identifying a set of goals of the user; and

applying weights of relative importance for each goal within the set of goals.

11. The method of claim 10 , comprising:

utilizing a weighted average of increases in successive probabilities of the user making progress over each goal to rank content items.

12. A non-transitory machine readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising:

utilizing a machine learning model to evaluate a goal of a user, user information, and a set of content items to generate predictions for the content items of how likely each content item will be a causation factor of the user making progress towards the goal in response to the user being provided with each content item, wherein the predictions for the content items comprise (i) a first predicted likelihood that viewing a first content item will cause the user to make progress towards the goal and (ii) a second predicted likelihood that viewing a second content item will cause the user to make progress towards the goal,

the machine learning model trained based upon data indicative of one or more activities of at least one of the user or one or more other users;

selecting a target content item, based upon the predictions generated utilizing the machine learning model, from the set of content items based upon the target content item having a predicted likelihood of being the causation factor above a threshold;

providing, via a network connection, the target content item to the user;

tracking, via one or more network connections, feedback comprising data indicative of one or more further activities indicative of progress of the user towards the goal after providing the target content item to the user; and

training the machine learning model, based upon the tracked feedback comprising the data indicative of the one or more further activities indicative of progress, to generate a trained machine learning model.

13. The non-transitory machine readable medium of claim 12 , wherein the tracking is performed through a goal measurement feedback channel corresponding to at least one of user input, output of device equipment, or input from a third party.

14. The non-transitory machine readable medium of claim 12 , wherein the user achieving the goal is an objective of the machine learning-model, and wherein the operations comprise:

utilizing output from a system, with a target objective different than the objective of the machine learning model, to rank the set of content items.

15. The non-transitory machine readable medium of claim 12 , wherein the operations comprise:

maintaining a user repository of age data, gender data, home location data, work location data, and media preference data of users;

maintaining a media repository of metadata about content items and relationships between content items corresponding to overlap of at least one of authorship data, theme data, location data, actors data, users experiencing content items, and time of users experiencing content items; and

applying the machine learning model to data within the user repository and the media repository for selecting the target content item.

16. A computing device comprising:

a processor; and

memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:

utilizing a machine learning model to evaluate a goal of a user, user information, and a set of content items to generate predictions for the content items of how likely each content item will be a causation factor of the user making progress towards the goal in response to the user being provided with each content item, wherein the predictions for the content items comprise (i) a first predicted likelihood that viewing a first content item will cause the user to make progress towards the goal and (ii) a second predicted likelihood that viewing a second content item will cause the user to make progress towards the goal,

selecting a target content item, based upon the predictions generated utilizing the machine learning model, from the set of content items based upon the target content item having a predicted likelihood of being the causation factor above a threshold;

providing, via a network connection, the target content item to the user;

tracking, via one or more network connections, feedback comprising data indicative of one or more further activities indicative of progress of the user towards the goal after providing the target content item to the user; and

training the machine learning model, based upon the tracked feedback comprising the data indicative of the one or more further activities indicative of progress, to generate a trained machine learning model.

17. The computing device of claim 16 , wherein the tracking is performed through a goal measurement feedback channel corresponding to at least one of user input, output of device equipment, or input from a third party.

18. The computing device of claim 16 , wherein the user achieving the goal is an objective of the machine learning model, and wherein the operations comprise:

utilizing output from a system, with a target objective different than the objective of the machine learning model, to rank the set of content items.

19. The computing device of claim 16 , wherein the operations comprise:

maintaining a user repository comprising at least one of age data, gender data, home location data, work location data, or media preference data of users; and

applying the machine learning model to data within the user repository for selecting the target content item.

20. The computing device of claim 16 , wherein the operations comprise:

maintaining a media repository of metadata about content items and relationships between content items corresponding to overlap of at least one of authorship data, theme data, location data, actors data, users experiencing content items, or time of users experiencing content items; and

applying the machine learning model to data within the media repository for selecting the target content item.