Content recommendation system
Disclosed are systems and methods for determining similarities in content preferences among a plurality of users and generating content recommendations based on a requesting user's content consumption history. A requesting user may access the recommendation system to request content items for consumption. The recommendation system may be configured to identify users having consumed the same or similar content items as the requesting user, and to determine a ratio of content items consumed by the requesting user and an identified user to the total number of content items previously consumed by the requesting user. In one embodiment, the system may determine a degree of similarity in content preferences between the two users based on an inverse proportion of a level of popularity associated with the content items consumed by the requesting user and the identified user (e.g., sampled user).
1. A method comprising:
determining a target user;
determining similarities in content item preferences between the target user and a plurality of candidate users by:
determining, for each of the candidate users, a respective quantity of commonly-disliked content items between the candidate user and the target user, and
ranking the plurality of candidate users based on the quantities of commonly-disliked content items, wherein the ranking gives preference to commonly-disliked content items based on popularity of the commonly-disliked content items;
selecting, based on the ranked candidate users, one or more candidate users for recommending content items to the target user; and
sending a content item recommendation, for the target user, based on content consumption histories of the selected one or more candidate users.
2. The method of claim 1 , wherein the ranking is also based on determining, for each of the plurality of candidate users, a ratio of:
the respective quantity of the commonly-disliked content items; to
a total quantity of content items disliked by the target user.
3. The method of claim 1 , wherein the ranking gives preference to the commonly disliked content items in proportion to an aggregated popularity value of the commonly-disliked content items.
4. The method of claim 1 , wherein sending the content item recommendation comprises verifying that the target user has not previously consumed a content item associated with the content item recommendation.
5. The method of claim 1 , wherein the popularity is based on quantities of times that the commonly-disliked content items have been accessed.
6. The method of claim 1 , wherein a selected candidate user of the selected one or more candidate users has a highest quantity of disliked content items, that are popular among other users, in common with the target user.
7. The method of claim 1 , further comprising providing a user interface to the target user, wherein the user interface is configured to receive user input selections indicating one or more modifications to the ranking of the plurality of candidate users.
8. A system comprising:
a user device associated with a target user; and
a server device;
wherein the server device comprises:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the server device to:
determine the target user;
determine similarities in content item preferences between the target user and a plurality of candidate users by:
determining, for each of the candidate users, a respective quantity of commonly-disliked content items between the candidate user and the target user, and
ranking the plurality of candidate users based on the quantities of commonly-disliked content items, wherein the ranking gives preference to commonly-disliked content items based on popularity of the commonly-disliked content items;
select, based on the ranked candidate users, one or more candidate users for recommending content items to the target user; and
send, based on content consumption histories of the selected one or more candidate users, a content item recommendation to the user device.
9. The system of claim 8 , wherein the instructions, when executed by the one or more processors, cause the server device to rank the plurality of candidate users further based on determining, for each of the plurality of candidate users, a ratio of:
the respective quantity of the commonly-disliked content items; to
a total quantity of content items disliked by the target user.
10. The system of claim 8 , wherein the instructions, when executed by the one or more processors, cause the server device to rank the plurality of candidate users further based giving preference to the commonly disliked content items in proportion to an aggregated popularity value of the commonly-disliked content items.
11. The system of claim 8 , wherein the instructions, when executed by the one or more processors, cause the server device to send the content item recommendation based on verifying that the target user has not previously consumed a content item associated with the content item recommendation.
12. The system of claim 8 , wherein the popularity is based on quantities of times that the commonly-disliked content items have been accessed.
13. The system of claim 8 , wherein a selected candidate user of the selected one or more candidate users has a highest quantity of disliked content items, that are popular among other users, in common with the target user.
14. The system of claim 8 , wherein the instructions, when executed by the one or more processors, cause the server device to provide a user interface at the user device, wherein the user interface is configured to receive user input selections indicating one or more modifications to the ranking of the plurality of candidate users.
15. A non-transitory computer readable medium storing instructions that, when executed, cause:
determining a target user;
determining similarities in content item preferences between the target user and a plurality of candidate users by:
determining, for each of the candidate users, a respective quantity of commonly-disliked content items between the candidate user and the target user, and
ranking the plurality of candidate users based on the quantities of commonly-disliked content items, wherein the ranking gives preference to commonly-disliked content items based on popularity of the commonly-disliked content items;
selecting, based on the ranked candidate users, one or more candidate users for recommending content items to the target user; and
sending a content item recommendation, for the target user, based on content consumption histories of the selected one or more candidate users.
16. The non-transitory computer readable medium of claim 15 , wherein the instructions, when executed, cause the ranking the plurality of candidate users further based on determining, for each of the plurality of candidate users, a ratio of:
the respective quantity of the commonly-disliked content items; to
a total quantity of content items disliked by the target user.
17. The non-transitory computer readable medium of claim 15 , wherein the instructions, when executed, cause the ranking the plurality of candidate users further based on giving preference to the commonly disliked content items in proportion to an aggregated popularity value of the commonly-disliked content items.
18. The non-transitory computer readable medium of claim 15 , wherein the instructions, when executed, cause the sending the content item recommendation based on verifying that the target user has not previously consumed a content item associated with the content item recommendation.
19. The non-transitory computer readable medium of claim 15 , wherein the popularity is based on quantities of times that the commonly-disliked content items have been accessed.
20. The non-transitory computer readable medium of claim 15 , wherein a selected candidate user of the selected one or more candidate users has a highest quantity of disliked content items, that are popular among other users, in common with the target user.
21. The non-transitory computer readable medium of claim 15 , wherein the instructions, when executed, cause providing a user interface at the user device, wherein the user interface is configured to receive user input selections indicating one or more modifications to the ranking of the plurality of candidate users.