Erik Bernhardsson    About

What’s up with music recommendations?

I just answered a Quora question about what, if any, are the differences in the algorithms that are behind recommendations for music and movies. Of course, every media type is different. For instance, there’s fundamental reasons why lat...

3D

Andy Sloane decided to call my 2D visualization and raise it to 3D. (Looks a little weird in the iframe but check out the link). It’s based on a LDA model with 200 topics, so the artists tend to stick to clusters where each cluster is a...

2D embedding of 5k artists = WIN

I’m at KDD in Chicago for a few days. We have a Spotify booth tomorrow, and I wanted to put together some cool graphics to show. I’ve been thinking about doing a 2D embedding of the top artists forever since I read about t-SNE and other ...

Delivering Music Recommendations

I’ve turned into a lazy bastard and I’m just posting presentations on this blog, but here’s one from Rohan Singh at Spotify talking about the backend infrastructure of the Discover page.

ML+Hadoop at NYC Predictive Analytics

I was just at the NYC Predictive Analytics meetup talking about how we build machine learning algorithms using Hadoop to power music recommendations. Great meetup, where we had two speakers, me and Blake Shaw from Foursquare. Blake talk...

More Luigi: Presentation from OSCON

I was in Portland, OR for a few days hanging out at OSCON. Was fun. I also talked a bit about Luigi: Next week I’m presenting at the NYC Predictive Analytics meetup together with Blake Shaw from Foursquare. The topic is ML + Hadoop. Wil...