Hi there, trying to leverage "similar movies" data (available through API) in my research on recommender systems. I have a couple of questions.

Has the list of similar movies for a given movie already been sorted based on relevance ?
How was this "similar set" created for each movie? To be precise, is it content-based similarity (say movies with similar attributes), or it is some sort of algorithmic recommendation based on viewership?

Thanks again for your input.