Intelligent content recommender for groups of users

1. A computer-implemented method for providing digital content based on a plurality of users, the method being executed by one or more processors and comprising:

receiving a request for digital content to be provided from a plurality of items of digital content;

determining a set of content scores for each item of digital content in the plurality of items of digital content, each content score in the set of content scores being specific to a user of the plurality of users, and a respective item of digital content;

calculating a combined score deviation for each item of digital content based on a difference between a minimum content score and a maximum content score of the set of content scores of a respective item of digital content;

determining a combined persona for two or more users of the plurality of users based on a history of items of digital content previously provided to the two or more users;

determining a combined persona score deviation for each item of digital content of the plurality of items of digital content;

filtering the plurality of items of digital content to provide one or more items of digital content that have a lowest combined persona score deviation among the plurality of items of digital content;

determining at least one candidate item of digital content from the one or more items of digital content, the at least one candidate item of digital content having a lowest combined score deviation among combined score deviations of the the one or more items of digital content; and

providing, by the one or more processors, the at least one candidate item of digital content.

2. The computer-implemented method of claim 1 , wherein the combined persona includes at least one content attribute for which the two or more users have previously provided feedback.

3. The computer-implemented method of claim 1 , wherein a content score specific to a user is determined based on a history of user consumption of items of digital content.

4. The computer-implemented method of claim 1 , wherein a content score specific to a user is determined based on feedback that the user has provided.

5. The computer-implemented method of claim 4 , wherein the feedback is associated with one or more content attributes.

6. The computer-implemented method of claim 4 , wherein the feedback includes a first feedback and a second feedback, the first feedback having a first weight in the content score and the second feedback having a second weight in the content score, the second weight being different from the first weight.

7. The computer-implemented method of claim 1 , further comprising:

receiving, by the one or more processors, a selected candidate item of digital content that is selected from the at least one candidate item of digital content by a user of the plurality of users; and

updating content scores of an item of digital content, wherein the item of digital content has at least one common content attribute with the selected candidate item of digital content.

8. The computer-implemented method of claim 1 , wherein the plurality of items of digital content comprise movies.

9. One or more non-transitory computer-readable storage media coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for providing digital content based on a plurality of users, the operations comprising:

receiving a request for digital content to be provided from a plurality of items of digital content;

determining a set of content scores for each item of digital content in the plurality of items of digital content, each content score in the set of content scores being specific to a user of the plurality of users, and a respective item of digital content;

calculating a combined score deviation for each item of digital content based on a difference between a minimum content score and a maximum content score of the set of content scores of a respective item of digital content;

determining a combined persona for two or more users of the plurality of users based on a history of items of digital content previously provided to the two or more users;

determining a combined persona score deviation for each item of digital content of the plurality of items of digital content;

filtering the plurality of items of digital content to provide one or more items of digital content that have a lowest combined persona score deviation among the plurality of items of digital content;

determining at least one candidate item of digital content from the one or more items of digital content, the at least one candidate item of digital content having a lowest combined score deviation among combined score deviations of the the one or more items of digital content; and

providing the at least one candidate item of digital content.

10. The computer-readable storage media of claim 9 , wherein the combined persona includes at least one content attribute for which the two or more users have previously provided feedback.

11. The computer-readable storage media of claim 9 , wherein a content score specific to a user is determined based on a history of user consumption of items of digital content.

12. The computer-readable storage media of claim 9 , wherein a content score specific to a user is determined based on feedback that the user has provided.

13. The computer-readable storage media of claim 12 , wherein the feedback includes a first feedback and a second feedback, the first feedback having a first weight in the content score and the second feedback having a second weight in the content score, the second weight being different from the first weight.

14. The computer-readable storage media of claim 9 , wherein operations further comprise:

receiving a selected candidate item of digital content that is selected from the at least one candidate item of digital content by a user of the plurality of users; and

updating content scores of an item of digital content, wherein the item of digital content has at least one common content attribute with the selected candidate item of digital content.

15. The computer-readable storage media of claim 9 , wherein the plurality of items of digital content comprise movies.

16. A system, comprising:

one or more processors; and

a computer-readable storage device coupled to the one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for providing digital content based on a plurality of users, the operations comprising:

receiving a request for digital content to be provided from a plurality of items of digital content;

determining a set of content scores for each item of digital content in the plurality of items of digital content, each content score in the set of content scores being specific to a user of the plurality of users, and a respective item of digital content;

calculating a combined score deviation for each item of digital content based on a difference between a minimum content score and a maximum content score of the set of content scores of a respective item of digital content;

determining a combined persona for two or more users of the plurality of users based on a history of items of digital content previously provided to the two or more users;

determining a combined persona score deviation for each item of digital content of the plurality of items of digital content;

filtering the plurality of items of digital content to provide one or more items of digital content that have a lowest combined persona score deviation among the plurality of items of digital content;

determining at least one candidate item of digital content from the one or more items of digital content, the at least one candidate item of digital content having a lowest combined score deviation among combined score deviations of the the one or more items of digital content; and

providing the at least one candidate item of digital content.

17. The system of claim 16 , wherein the combined persona includes at least one content attribute for which the two or more users have previously provided feedback.