Abstract: Devices, systems, and methods for machine learning-based micro-category generation may include a method including identifying, for a respective cluster of content titles or items, a top-K most representative group of the content titles or items; generating, by a machine learning model, based on a first input prompt, the common theme of the top-K most representative group; generating, by the machine learning model, based on the second input prompt and filtering, a group of content titles or items matching the common theme; generating, by the machine learning model, based on a third input prompt, a name for the group of content titles or items matching the common theme; and presenting the group of content titles or items matching the common theme and the name for the group of content titles or items matching the common theme via a user interface of a streaming media application.

Abstract: A computer-implemented method includes grouping video title items into clusters based on video title characteristics. A system processor identifies a connecting characteristic of the video title characteristics that associates a first cluster of video title items and a second cluster of video title items. The system creates a user profile associated with a video content account based at least in part on a history of streamed/downloaded video title items by identifying a video title characteristic associated with two or more video content items streamed/downloaded by the video content account, and grouping the two or more video content items based at least in part on the first cluster of video title items and the second cluster of video title items. The system provides a system-generated user profile that identifies user specific video content from an account having multiple users streaming content in association with the account.