Notification policies

1. A method comprising:

by one or more computing devices, receiving an indication of an occurrence of a triggering event for one or more notifications of user-generated content relevant to one or more users, wherein the notifications are sent to one or more of the users through one or more of a plurality of notification channels, and wherein each notification channel is associated with one or more software applications;

by one or more computing devices, accessing a plurality of notification policies associated with the software applications, wherein:

each of the software applications has at least one associated notification policy;

at least one of the notification policies associated with a first one of the software applications is interrelated with at least one other notification policy associated with a second one of the software applications;

by one or more computing devices, applying a feature vector corresponding to one or more of the users to a machine-learning (ML) model, wherein the ML model is based on click-through rates (CTR) of the one or more users with regard to a type associated with one or more of the notifications; and

by one or more computing devices, sending one or more notifications to one or more users through one or more of the plurality of notification channels based at least in part on the output of one or more interrelated notification policies and the ML model.

2. The method of claim 1 , wherein the interrelationship comprises an output of at least one of notification policies associated with the first one of the software applications provides an input to at least one other notification policy associated with the second one of the software applications.

3. The method of claim 1 , further comprising:

accessing data of previous interactions by the user with regard to the first one and second one of the software applications; and

determining a modification to the first one or second one of the software applications based at least in part on the accessed data.

4. The method of claim 3 , wherein determining one or more of the modifications comprises applying a machine-learning algorithm to the data of previous interactions by the user with regard to the first one or second one of the software applications.

5. The method of claim 1 , wherein:

each notification channel comprises a plurality of notification policies associated with a plurality of components;

each of the components has at least one associated notification policy; and

at least one of the notification policies associated with a first one of the components is interrelated with at least one other notification policy associated with a second one of the categories.

6. The method of claim 1 , wherein each of the sent notifications has a notification score higher than the threshold value of the respective notification policy.

7. The method of claim 1 , further comprising ranking the notifications based at least in part on the notification score.

8. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

receive an indication of an occurrence of a triggering event for one or more notifications of user-generated content relevant to one or more users, wherein the notifications are sent to one or more of the users through one or more of a plurality of notification channels, and wherein each notification channel is associated with one or more software applications;

access a plurality of notification policies associated with the software applications, wherein:

each of the software applications has at least one associated notification policy;

at least one of the notification policies associated with a first one of the software applications is interrelated with at least one other notification policy associated with a second one of the software applications;

apply a feature vector corresponding to one or more of the users to a machine-learning (ML) model, wherein the ML model is based on click-through rates (CTR) of the one or more users with regard to a type associated with one or more of the notifications; and

send one or more notifications to one or more users through one or more of the plurality of notification channels based at least in part on the output of one or more interrelated notification policies and the ML model.

9. The media of claim 8 , wherein the interrelationship comprises an output of at least one of notification policies associated with the first one of the software applications provides an input to at least one other notification policy associated with the second one of the software applications.

10. The media of claim 8 , wherein the software is further operable to:

access data of previous interactions by the user with regard to the first one and second one of the software applications; and

determine a modification to the first one or second one of the software applications based at least in part on the accessed data.

11. The media of claim 10 , wherein the software is further operable to apply a machine-learning algorithm to the data of previous interactions by the user with regard to the first one or second one of the software applications.

12. The media of claim 8 , wherein:

each notification channel comprises a plurality of notification policies associated with a plurality of components;

each of the components has at least one associated notification policy; and

at least one of the notification policies associated with a first one of the components is interrelated with at least one other notification policy associated with a second one of the components.

13. The media of claim 8 , wherein each of the sent notifications has a score higher than the threshold value of the respective notification policy.

14. The media of claim 8 , wherein the software is further operable to rank the notifications based at least in part on the notification score.

15. A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:

receive an indication of an occurrence of a triggering event for one or more notifications of user-generated content relevant to one or more users, wherein the notifications are sent to one or more of the users through one or more of a plurality of notification channels, and wherein each notification channel is associated with one or more software applications;

access a plurality of notification policies associated with the software applications, wherein:

each of the software applications has at least one associated notification policy;

at least one of the notification policies associated with a first one of the software applications is interrelated with at least one other notification policy associated with a second one of the software applications;

apply a feature vector corresponding to one or more of the users to a machine-learning (ML) model, wherein the ML model is based on click-through rates (CTR) of the one or more users with regard to a type associated with one or more of the notifications; and

send one or more notifications to one or more users through one or more of the plurality of notification channels based at least in part on the output of one or more interrelated notification policies and the ML model.

16. The system of claim 15 , wherein the interrelationship comprises an output of at least one of notification policies associated with the first one of the software applications provides an input to at least one other notification policy associated with the second one of the software applications.

17. The system of claim 15 , wherein the processors are further operable to:

access data of previous interactions by the user with regard to the first one and second one of the software applications; and

determine a modification to the first one or second one of the software applications based at least in part on the accessed data.

18. The system of claim 17 , wherein the processors are further operable to apply a machine-learning algorithm to the data of previous interactions by the user with regard to the first one or second one of the software applications.

19. The system of claim 15 , wherein:

each notification channel comprises a plurality of notification policies associated with a plurality of components;

each of the components has at least one associated notification policy; and

at least one of the notification policies associated with a first one of the components is interrelated with at least one other notification policy associated with a second one of the components.

20. The system of claim 15 , wherein each of the sent notifications has a score higher than the threshold value of the respective notification policy.