Content recommendation system and method-based implicit ratings
A content recommendation system that recommends content based on previous user content information and information regarding the user and user device. The system is capable of accurately recommending content using collaborative filtering by comparing the user's profile to other user profiles. User profiles rely on implicit ratings to determine user preferences. Implicit ratings may be determined by collecting the content that a user consumed, in addition to user and user device information. The system recommends content that similar users have consumed. The system is also able to identify and recommend trending content by analyzing changes in metrics over time. The system may also rely on automatic content recognition to identify content that the user is consuming without requiring active user input.
1. A method for recommending trending content comprising the steps of:
identifying trending content in a profile database by a change in one or more metrics of aggregated data in said profile database;
generating a trending profile based on aggregated profiles of trending users, wherein the processor identifies trending users as users who have consumed said trending content and wherein said processor retrieves user profiles of trending users from said profile database;
retrieving by a processor from said profile database user profiles similar to said trending profile and delivering said user profiles similar to said trending profile to the recommendation engine, wherein the processor uses collaborative filtering to only deliver user profiles that are both similar to the trending profile and do not indicate consumption of said trending content; and
recommending the trending content by a recommendation engine to users who have user profiles that are both similar to the trending profile and do not indicate consumption and said trending content.
2. The method according to claim 1 further comprising the step of:
generating the trending profile by additionally using aggregated user information and other metadata of the trending users.
3. The method according to claim 1 further comprising the step of:
determining trending content within a subset of user profiles in the profile database by the processor, wherein the subset is determined by user information and other metadata indicating geographic location of the user.
4. The method according to claim 1 further comprising the step of:
filtering a subset of the users to be recommended trending content by the recommendation engine, wherein the subset is determined by user information and other metadata indicating time period of a day when the user consumes content.