Methods, systems, and apparatuses for content recommendations based on user activity

An apparatus comprising:

• one or more processors and;
• processor-executable instructions that, when executed by the one or more processors, cause the apparatus to:
• receive, by an analytics subsystem, first activity data indicative of a plurality of first engagements of a first user device with a client application, wherein the plurality of first engagements are associated with a first plurality of media assets;
• determine metadata associated with each media asset of the first plurality of media assets, wherein the metadata associated with each media asset of the first plurality of media assets comprises at least one first media asset classification;
• determine, based on the at least one first media asset classification, at least one machine learning model of a plurality of machine learning models;
• determine, by the at least one machine learning model, based on the first activity data, at least one content recommendation, wherein the at least one content recommendation comprises at least one media asset associated with at least one second media asset classification;
• and
• send, to the first user device, the at least one content recommendation.