Notification Click-Through Rate (CTR) Thresholds

• US 20170118304A1
• Filed: 10/26/2015
• Published: 04/27/2017
• Est. Priority Date: 10/26/2015
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Ratiu, Florin, Birchall, Andrew Alexander, Park, David S., Ilic, Aleksandar, Schloss, Nathan Paul, Rajendran, Vasanth Kumar, Li, Yiyu, Varin, Patrick Jonathan, Stojkovic, Branislav
• Granted Patent: US 10,291,741 B2
• Time in Patent Office: Days
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/53 using third party service providers
• CPC Class Codes: H04L 67/55 Push-based network services
• CPC Class Codes: H04L 67/565 Conversion or adaptation of application format or content adding application control or application functional data H04L67/561

Abstract

In one embodiment, a method includes receiving a number of notifications of activity relevant to a user. Each notification has an associated type. The method also includes calculating an estimated click-through rate (CTR) for each notification based at least in part on the type associated with each notification; determining a push threshold value for each notification based at least in part on the estimated CTR for each notification; and sending one or more of the notifications to the user. Each of the sent notifications has a push threshold value higher than a pre-determined push threshold value.

Claims

1. A method comprising:

by a computing device, receiving a plurality of notifications of activity relevant to a user, wherein each notification has an associated type;

by the computing device, calculating an estimated click-through rate (CTR) for each notification based at least in part on the type associated with each notification;

by the computing device, determining a push threshold value for each notification based at least in part on the estimated CTR for each notification; and

by the computing device, sending one or more of the notifications to the user, wherein each of the sent notifications has a push threshold value higher than a pre-determined push threshold value.

2. The method of claim 1, wherein the estimated CTR is based at least in part on a user history associated with each type of notification.

3. The method of claim 2, wherein the user history comprises a CTR of previous notifications having a same type as the received notifications.

4. The method of claim 3, wherein the estimated CTR is calculated based at least in part on a CTR of previous notifications of a same type measured over a pre-determined period of time.

5. The method of claim 2, wherein the user history comprises a delivery pattern of the user, and wherein a time that the notifications are sent is based at least in part on the delivery pattern.

6. The method of claim 1, wherein the estimated CTR is calculated based at least in part on one or more negative signals from previous notifications having a same type as the received notifications.

7. The method of claim 6, wherein the negative signals comprise:

a low CTR;

an unsubscribe input;

a disable push input;

or

an indication of an application logout.

8. The method of claim 1, wherein the unsubscribe input is based on the type of the received notification, content of the received notification, indication of disinterest, or group-related factors of the notification.

9. The method of claim 1, wherein the user is represented by a first user node in a social graph associated with a social-networking system, wherein the activity is associated with another user, wherein the other user is represented by a second user node, and wherein the estimated CTR is further based on an affinity between the first and second user nodes.

10. The method of claim 9, wherein the activity relevant to the user is represented as an edge connecting the first and second user nodes.

11. The method of claim 9, wherein the types of notifications comprise posts, people you may know, trending topic, or advertisement from the social-networking system.

12. The method of claim 1, wherein the sending of the one or more notifications comprises sending the notifications in accordance to a delivery policy, wherein the delivery policy comprises:

whether to send the notifications to the user;

when to send the notifications to the user;

identification of an endpoint associated with the user to send the notifications;

or

identification of a communication media to send the notifications to the user in.

13. The method of claim 12, wherein the estimated CTR is further based on the identified communication media of each notification.

14. The method of claim 12, wherein the estimated CTR is further based on the identified endpoint of each notification.

15. The method of claim 1, further comprising:

determining a number of sent notifications of a particular type in real-time;

calculating a measured CTR based at least in part on comparing a number of conversions with the number of sent notifications; and

modifying the push threshold value for notifications of the particular type based at least in part on the calculation.

16. The method of claim 15, wherein the modification comprises increasing the push threshold value for notifications of the particular type in response to the measured CTR being lower than the estimated CTR.

17. The method of claim 15, wherein the modification comprises decreasing the push threshold value for notifications of the particular type in response to the measured CTR being higher than the estimated CTR.

18. The method of claim 1, wherein one or more notifications having a push threshold value higher than a pre-determined pre-fetching threshold value is pre-fetched by a client device of the user, and wherein the pre-determined pre-fetching threshold value is higher than the pre-determined push threshold value.

19. One or more computer-readable non-transitory storage media embodying software configured when executed to:

receive a plurality of notifications of activity relevant to a user, wherein each notification has an associated type;

calculate an estimated click-through rate (CTR) for each notification based at least in part on the type associated with each notification;

determine a push threshold value for each notification based at least in part on the estimated CTR for each notification; and

send one or more of the notifications to the user, wherein each of the sent notifications has a push threshold value higher than a pre-determined push threshold value.

20. A device comprising:

one or more processors; and

one or more computer-readable non-transitory storage media coupled to the processors and embodying software configured when executed to;

receive a plurality of notifications of activity relevant to a user, wherein each notification has an associated type;

calculate an estimated click-through rate (CTR) for each notification based at least in part on the type associated with each notification;

determine a push threshold value for each notification based at least in part on the estimated CTR for each notification; and

send one or more of the notifications to the user, wherein each of the sent notifications has a push threshold value higher than a pre-determined push threshold value.