Abstract: The systems and methods described herein receive a fitness goal or target (e.g., a user wants to be stronger, or run faster, or bike longer within a certain heart rate zone) as seed input into a guidance system, which generates a personalized plan of recommended classes/activities for the user based on their goal/target. At different points along the plan, the guidance system may modify or update its recommendations with different or enhanced classes/activities, in order to keep the user on their target or goal.

Abstract: Systems and methods that facilitate and/or enable a connected fitness platform to dynamically rank and select rows (or groups) of content to display to a user are described. For example, a platform may dynamically rank and present rows of exercise classes to a user of an exercise machine via a home screen or other portal into the content provided by the platform.

Abstract: Systems and methods that generate and perform class or content recommendations to users of a connected fitness platform are described. In some embodiments, the systems and methods may address a cold-start problem that often arises in connected fitness platforms, providing guidance to new users of the platform as they navigate through fitness content (of varying difficulty or experience levels) of the platform. The systems and methods introduce and adapt a transformer model to determine classes or content to recommend to new users of the platform.

Abstract: The systems and methods described herein facilitate an enhanced user experience within a connected fitness system. For example, the systems and methods can enhance and/or personalize a homescreen experience and interface for a user of a connected fitness platform. The homescreen experience, when personalized, can provide a user with enhanced or specifically tailored rows of content, such as recommended classes or activities, for selection by the user.