Big Data

Spotify intern dreams up better music recommendations through deep learning

Image Credit: Jon Åslund/Flickr

Spotify’s music-recommendation system has already become intelligent, thanks to machine learning that happens behind the scenes. But an academic researcher who’s been spending time at the company’s New York office has been looking at ways to use deep learning to surface songs based on their content.

If Spotify puts researcher Sander Dieleman’s work into production, the company could have a shot at improving user experience enough to help it stand out against competitors like Rdio, Songza, and Beats. And rather than merely playing music that people might already be familiar with, Spotify could become more of a tool for people to discover new or unpopular music.

“We want to be able to recommend new music right when it is released, and we want to tell listeners about awesome bands they have never heard of,” Dieleman wrote yesterday in an extensive blog post on his research. “To achieve these goals, we will need to use a different approach.”

Deep learning is a specialized sort of machine learning, one that involves training systems called artificial neural networks on lots of information derived from audio, images, and other inputs, and then presenting the systems with new information and receiving inferences about it in response.

In the past few years tech giants like Google, Microsoft, and Baidu have devoted resources to it. More recently, web companies like Facebook, Netflix, and Twitter have waded in to the area with acquisitions, major hires, and early research. Now we can add Spotify to the list of companies interested in improving their services with deep learning.

At Spotify, Dieleman is building on convolutional neural networks, a deep-learning technique that Facebook’s Yann Lecun popularized, particularly in association with images. Dieleman trained his neural networks on short slices of songs and then started creating playlists based on certain features they observed in the audio.

Playlists pick up on bass drums, vibrato singing, and ambiance, among other traits. But Dieleman went further and even gathered songs with a similar pitch, guitar distortion, and other qualities.

Dieleman thinks the neural networks might be starting to pick up on certain characteristics in music like the appearance of chord progressions in certain genres. If that is actually happening, it’d be pretty fascinating. Just imagine how fun it’d be to listen to a playlist of 10 songs with chord progressions kind of like the one in, say, “Baba O’Riley” by The Who.

And the system might even be picking up on the language of song lyrics, Dieleman wrote.

The neural networks have their issues, he acknowledged, although they’re not bad, considering that they only taking the music itself into consideration — and samples of songs, at that.

Now it’s up to Spotify to decide if putting the deep learning-based recommendation system into production, even if only to weed out bad recommendations.

“Spotify already uses a bunch of different information sources and algorithms in their recommendation pipeline, so the most obvious application of my work is simply to include it as an extra signal,” Dieleman wrote.

Certainly that could prove useful for Dieleman, who himself is a follower of progressive metal.

“One of my main goals with this work is to make it possible to recommend new and unpopular music. I hope that this will help lesser known and up and coming bands, and that it will level the playing field somewhat by enabling Spotify to recommend their music to the right audience,” he wrote.

More information:

Spotify is a Swedish DRM-based music streaming service offering streaming of selected music from a range of major and independent record labels, including Sony, EMI, Warner Music Group, and Universal.[ Launched in October 2008 by Swedi... read more »

Powered by VBProfiles


VentureBeat is studying mobile marketing automation. Chime in, and we’ll share the data.
24 comments
Pedro Rasera
Pedro Rasera

Spotify really ought to learn from Pandora, which, in my humble opinion, does a far better job of suggesting music based on the ACTUAL music, not their metadata.

RD Ji
RD Ji

Ed Lee Stephen Chen :o

Timothy O'Brien
Timothy O'Brien

Wow thats great if only I could log back into my account grrr

Gaurav Ragtah
Gaurav Ragtah

Most tech companies pay their interns really well.

Nhan T. Dao
Nhan T. Dao

Jason Lee you should give this guy your lunch money.

Nicholas M. Cummings
Nicholas M. Cummings

Norbert the intern clearly already knew what they were doing or they wouldn't have built something so productive. Why are companies cheap fucks who want any means they can get to receive free labor? A coder building a machine learning algorithm is providing a hell of a lot more value than an intern doing low grade clerical work

Norbert Rum
Norbert Rum

Why should they get paid for learning?

Alexander Pajor
Alexander Pajor

About damn time! I've been complaining for two years now

Mark McDermott
Mark McDermott

Really? Because the radio function just plays the same songs on a loop. I suppose a bit like commercial radio. But we hope for better!

Thomas Lidforss
Thomas Lidforss

Spotify is getting smarter and over time. Better than the competition

Gus Mastrapa
Gus Mastrapa

Maybe use some of that intelligence to differentiate between bands with the same name?