Computer processes for predicting media item popularity

• US 9,753,988 B1
• Filed: 09/23/2013
• Issued: 09/05/2017
• Est. Priority Date: 09/23/2013
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: McGilliard, Christopher Lon
• Primary Examiner(s): Herndon, Heather
• Assistant Examiner(s): Nguyen, Merilyn
• Application Number:
  US14/034,430
• Time in Patent Office: 1,443 Days
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/635 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: H04N 21/44204 Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched monitoring of user activities for profile generation for accessing a video database G06F16/739; protecting generic digital content where the protection is independent of the precise nature of the content G06F21/10; arrangements for monitoring the use made of the broadcast services in broadcast systems H04H60/31

Abstract

Systems and methods are disclosed that identify users of a media distribution system that tend to consume popular media items prior to such media items gaining popularity. For example, a set of early adopters may be identified that tend to listen to music associated with particular artists before such artists become popular. The systems and methods disclosed may also utilize identified early adopters to determine relatively obscure or unpopular media items (or creators thereof) that are likely to become popular in the future. Illustratively, an obscure artist whose content is commonly consumed by early adopters can be identified as potentially achieving widespread popularity in the future. These media items predicted to become popular or media item creators may then be recommended to other users of the media distribution system.

Claims

1. A computer-implemented method of identifying musical artists that are likely to become popular, the computer-implemented method comprising:

determining a first set of musical artists have achieved a selected popularity level on a network-based music distribution system based at least in part on one or more popularity metrics;

retrieving artist interaction information reflecting user interaction with the music distribution system regarding the first set of musical artists;

determining a set of users of the music distribution system that interacted with content related to individual artists of the first set of musical artists prior to popularity of the individual artists, wherein the set of users are determined based at least in part on the artist interaction information;

assigning scores to individual users of the set of users, wherein a score of an individual user is based at least in part on a length of time between i) an initial interaction of the individual user with content related to the individual artists and ii) a point in time at which the individual artists achieved the selected popularity level;

retrieving early adopter interaction information reflecting interactions of the determined set of users with content of a second set of artists not yet popular on the music distribution system;

ranking the second set of artists based at least in part on the early adopter interaction information and the scores of individual users corresponding to the early adopter interaction information;

selecting at least one artist of the second set of artists based at least in part on the ranking to form a recommendation; and

transmitting the recommendation of the selected at least one artist to at least one user of the music distribution system;

wherein said method is performed entirely by a computer system that comprises one or more computing devices.

2. The computer-implemented method of claim 1, wherein the one or more popularity metrics comprise at least one of a level of interaction with content of an artist on the network-based music distribution system, a level of interaction with the artist on an external system, an externally published popularity ranking of the artist, or reported sales of the artist by an external organization.

3. The computer-implemented method of claim 2, wherein the level of interaction with the artist on the network-based music distribution system includes at least one of a number of times users of the network-based music distribution system have consumed media content associated with the artist, viewed information regarding the artist or media content associated with the artist, searched for the artist or media content associated with the artist, commented on the artist or media content associated with the artist, reviewed the artist or media content associated with the artist, or rated the artist or media content associated with the artist.

4. The computer-implemented method of claim 2, wherein the external system is a social networking system, and wherein the level of interaction with the artist on the external system includes at least one of a number of posts regarding the artist on the social networking system, a number of users following the artist on the social networking system, or a number of endorsements of the artist on the social networking system.

5. The computer-implemented method of claim 1, wherein the recommendation of the at least one artist is included within at least one of a display page output by the music distribution system to a computing device associated with the at least one user or an electronic message transmitted to the computing device associated with the at least one user by the music distribution system.

6. A system for identifying media item creators predicted to become popular, the system comprising:

a data store configured to store user interaction information reflective of interaction of users with media items associated with a media information system; and

a computer system comprising one or more computing devices, said computer system configured with specific computer-executable instructions to at least;

identify one or more popular media item creators based at least in part on the user interaction information, wherein each of the one or more popular media item creators satisfies a set of popularity criteria;

determine a set of users of the media information system that interacted with content related to individual media item creators of the one or more popular media item creators prior to popularity of the respective popular media item creators, wherein the set of users are determined based at least in part on the user interaction information;

assign scores to individual users of the set of users, wherein a score of an individual user is based at least in part on a length of time between i) an initial interaction of the individual user with content related to the respective popular media item creators and ii) a point in time at which the respective popular media item creators satisfied the set of popularity criteria;

process user interaction information associated with the determined set of users to identify a set of non-popular media item creators on the media information system interacted with by the set of users;

rank the set of non-popular media item creators based at least in part on a level of interaction of the set of users with content of the non-popular media item creators and the scores of individual users of the set of users;

generate a recommendation of at least one media item creator of the ranked set of non-popular media item creators to at least one user of the media information system based at least in part on a rank of the at least one media item creator; and

transmit the recommendation of the at least one media item creator to a computing device associated with the at least one user.

7. The system of claim 6, wherein the media item creator is at least one of a band, an artist, an author, an editor, an engineer, a technician, or a producer of media items.

8. The system of claim 6, wherein the computing system is further configured to score the determined set of users based at least in part on one or more of a timing of each of the set of users'"'"' interaction with respective popular media item creators of the set of popular media item creators or a number of interactions of each of the set of users with respective popular media item creators of the set of popular media item creators.

9. The system of claim 6, wherein the recommendation is transmitted via at least one of a display page or electronic message transmitted by the one or more computing devices to the computing device of the at least one user.

10. The system of claim 6, wherein the one or more popular media item creators are associated with a specific geographical area.

11. Non-transitory computer storage having stored thereon executable instructions that direct a computer system comprising one or more computing devices to perform a process that comprises:

determining, based on artist popularity data and recorded behaviors of users, a plurality of early adopter users that have previously listened to music of popular musical artists before such popular musical artists became popular;

assigning scores to individual early adopter users of the plurality of early adopter users, wherein a score of an individual early adopter user is based at least in part on a length of time between i) an initial interaction of the individual early adopter user with individual popular musical artists and ii) a point in time at which the individual popular musical artists became popular;

identifying a set of musical artists that, based on recorded behaviors of users, have not yet reached a selected popularity level;

ranking the set of musical artists based at least in part on scores of the individual early adopter users and how frequently the early adopter users listen to music of the set of musical artists;

generating, based at least partly on the scores of the individual early adopter users and a measure of how frequently the early adopter users listen to music of the musical artists, scores for individual musical artists of the set of musical artists that represents a likelihood that the respective individual musical artists will at least reach the selected popularity level;

generating, from at least the scores of the individual musical artists, a recommendation of at least one musical artist; and

transmitting the recommendation to a computing device of a user.

12. The non-transitory computer storage of claim 11, wherein the score assigned to individual early adopter users of the plurality of early adopter users is further based at least in part on demographic information associated with the individual early adopter users of the plurality of early adopter users.

13. The non-transitory computer storage of claim 11, wherein the process further comprises providing a reward to at least one of the plurality of early adopter users.