Mapping the World of Music Using Machine Learning: Part 1
Ravi Mody

Matt Quaine — Matrix factorization does this grouping for us; the only thing we’re providing about the artists is which users are listening to which artist. You could approximately read that list as “people who listen to Michael Jackson also listen to…” (the actual algorithm is more complicated than this, but that is what is being optimized, globally). I hope that makes sense!

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.