This month we have Erik Bernhardsson, the tech lead of the Discovery team at Spotify, presenting "Music recommendations at Spotify". Here's his abstract and bio:
Spotify uses a range of large scale machine learning methods to find interesting music recommendations. Using large amounts of implicit data, collaborative filtering is behind features such as radio, related artists, and a number of soon to be released features. These are powered by matrix factorization and other methods that have been scaled up to 100s of billions of data points.
Erik is the tech lead of the Discovery team at Spotify and has been with the company since 2008.