Automatically labeling clusters of media content consumers
An analytics platform configured to create clusters of media content consumers and to automatically generate human-readable, text labels that describe each of the created clusters is disclosed. An analytics platform may use any of a number of clustering algorithms to group a population of media content consumers into a set of user clusters based on viewing history data, user profile data, and/or any other data associated with the consumers. Furthermore, the analytics platform may be configured to create, based on the viewing history data and/or other data associated with a selected sample of users from each cluster, a text label for each cluster. For example, if viewing history data for a population of users includes channel and genre identifiers associated with media content items accessed by users of the population, a generated text label may provide an indication of channels and/or genres popular with users of each particular cluster.
1. A method comprising:
creating, by a server, a plurality of user clusters based on media content viewing history data stored for each user of a plurality of users; and
for each particular user cluster of the plurality of user clusters:
selecting one or more sample users from the particular user cluster;
retrieving, for each sample user from the one or more sample users, viewing history data for the sample user over a specified time range;
creating one or more matrices for the one or more sample users, each matrix of the one or more matrices indicating a number of times a media device associated with a sample user accessed a media content item associated with one or more content identifiers;
determining, based on the created one or more matrices, a pattern of frequent genre identifiers identified for the one or more sample users within the created one or more matrices;
determining, based on the created one or more matrices, a pattern of frequently accessed channel identifiers identified for the one or more sample users within the created one or more matrices;
creating a composite text label for the user cluster based on the determined pattern of frequent genre identifiers, wherein the composite text label comprises a first portion based on the frequent genre identifiers and a second portion based on the frequent channel identifiers; and
storing the composite text label in association with the user cluster.
2. The method of claim 1 , wherein a number of user clusters created is based on a user selected value.
3. The method of claim 1 , further comprising:
determining, for each user cluster of the plurality of user clusters, an average viewing history based on a number of times users of the user cluster accessed any media content item;
wherein selecting the one or more sample users from the user cluster is based on selecting users from the user cluster with viewing histories similar to the average viewing history.
4. The method of claim 1 , further comprising:
determining an average viewing history based on a number of times users of the plurality of users accessed any media content item;
wherein selecting the one or more sample users from the user cluster is based on selecting users from the user cluster with viewing histories similar to the average viewing history.
5. The method of claim 1 , wherein the one or more content identifiers include at least a channel identifier and a genre identifier.
6. The method of claim 1 , wherein the one or more content identifiers include at least a channel identifier and a genre identifier; and
wherein the text label is based on one or more channel identifiers and one or more genre identifiers.
7. The method of claim 1 , further comprising causing display of a graphical user interface including display of the text label in association with a visual representation of the user cluster.
8. The method of claim 1 , wherein the specified time range includes all available viewing history.
9. The method of claim 1 , wherein each user cluster of the plurality of user clusters is associated with a separate text label.
10. The method of claim 1 , wherein a first matrix of the one or more matrices includes counts of occurrences of the one or more sample users accessing media content items associated with channel identifiers, and a second matrix of the one or more matrices includes counts of occurrences of the one or more sample users accessing media content items associated with genre identifiers.
11. One or more non-transitory computer-readable storage media, storing instructions, which when executed by one or more processors, causes:
creating, by a server, a plurality of user clusters based on media content viewing history data stored for each user of a plurality of users; and
for each particular user cluster of the plurality of user clusters:
selecting one or more sample users from the particular user cluster;
retrieving, for each sample user from the one or more sample users, viewing history data for the sample user over a specified time range;
creating one or more matrices for the one or more sample users, each matrix of the one or more matrices indicating a number of times a media device associated with a sample user accessed a media content item associated with one or more content identifiers;
determining, based on the created one or more matrices, a pattern of frequent genre identifiers identified for the one or more sample users within the created one or more matrices;
determining, based on the created one or more matrices, a pattern of frequently accessed channel identifiers identified for the one or more sample users within the created one or more matrices;
creating a composite text label for the user cluster based on the determined pattern of frequent genre identifiers, wherein the composite text label comprises a first portion based on the frequent genre identifiers and a second portion based on the frequent channel identifiers; and
storing the composite text label in association with the user cluster.
12. The one or more non-transitory computer-readable storage media of claim 11 , wherein a number of user clusters created is based on a user selected value.
13. The one or more non-transitory computer-readable storage media of claim 11 , wherein the instructions, when executed by the one or more processors, further causes:
determining, for each user cluster of the plurality of user clusters, an average viewing history based on a number of times users of the user cluster accessed any media content item;
wherein selecting the one or more sample users from the user cluster is based on selecting users from the user cluster with viewing histories similar to the average viewing history.
14. The one or more non-transitory computer-readable storage media of claim 11 , wherein the instructions, when executed by the one or more processors, further causes:
determining an average viewing history based on a number of times users of the plurality of users accessed any media content item;
wherein selecting the one or more sample users from the user cluster is based on selecting users from the user cluster with viewing histories similar to the average viewing history.
15. The one or more non-transitory computer-readable storage media of claim 11 , wherein the one or more content identifiers include at least a channel identifier and a genre identifier.
16. The one or more non-transitory computer-readable storage media of claim 11 , wherein the one or more content identifiers include at least a channel identifier and a genre identifier; and wherein the text label is based on one or more channel identifiers and one or more genre identifiers.
17. The one or more non-transitory computer-readable storage media of claim 11 , wherein the instructions, when executed by the one or more processors, further causes display of a graphical user interface including display of the text label in association with a visual representation of the user cluster.
18. The one or more non-transitory computer-readable storage media of claim 11 , wherein the specified time range includes all available viewing history.
19. The one or more non-transitory computer-readable storage media of claim 11 , wherein each user cluster of the plurality of user clusters is associated with a separate text label.
20. The one or more non-transitory computer-readable storage media of claim 11 , wherein a first matrix of the one or more matrices includes counts of occurrences of the one or more sample users accessing media content items associated with channel identifiers, and a second matrix of the one or more matrices includes counts of occurrences of the one or more sample users accessing media content items associated with genre identifiers.