| CPC H04N 21/251 (2013.01) | 22 Claims |
|
10. A computing system for candidate ranking for content recommendation, comprising:
one or more memories; and
at least one processor each coupled to at least one of the memories and configured to perform operations comprising:
receiving category candidates over a network, wherein each of the category candidates comprises content candidates associated with one or more applications operating on media devices;
receiving time series data associated with the content candidates, wherein the time series data comprises a time period of user interaction with one of the one or more applications in a session;
ranking the category candidates based on a machine learning model, wherein the machine learning model is trained using a learning algorithm based on the time series data;
generating a popularity score for one or more of the content candidates, wherein the popularity score comprises a number of times a particular content candidate has been searched for;
ranking the content candidates in each of the category candidates based on the time series data and the popularity score;
causing the ranked category candidates and the ranked content candidates to be outputted for display;
receiving feedback indicating a subset of the ranked content candidates have not been interacted with by one or more users; and
reducing the ranking of one or more of the subset of the ranked content candidates based on the feedback.
|