I’m an eMusic subscriber and supporter and noticed that they’ve overhauled their homepage centered around a new music recommendation engine called MediaUnbound. Now, when you sign into the site as a member, you’re presented with a grid of music you’ll like made up of personalized recommendations based upon your history. You can also sort the list by new arrivals.
I’ve been checking out the recommendations but am cautiously optimistic. Like any music recommendation service I’ve used, I don’t expect much. Most of them are disappointing, especially if you’re an avid music fan. But I understand eMusic’s need to upgrade. As a subscription based model, it’s important that their members find music they like. Otherwise, they’re apt to cancel.
What makes this new music recommendation service, MediaUnbound, supposedly unique is that it combines both algorithmic and human inputs to try to come up with better recommendations for users right from the start. And how are MediaUnbound’s human inputs different from say Pandora? This is where the story gets interesting, or amusing at the least. MediaUnbound CEO Michael Papish answers this question in a recent TechCrunch post and added a most amusing critique of other music recommendation services in existence.
On Pandora’s human input process:
Pandora has created a feature factory of humans chained to headphones attempting to objectively rate the sonic features of every song ever made (well, ok, only ~200k hand-picked songs). We think this is a horrible use of use of the creative, constructive, opinionated, and (sometimes argumentative) resource called the human music geek.
On the rest of the music recommendation technologies out there:
—Pandora. Purely sonic-based as determined by team of human experts classifying every song into features. Not scalable. One-trick pony only able to determine that one song sounds like another song, not anything about user preference or other personalized recommendations.
—iLike. Purely algorithm-based utilizing only data from other iLike members. Service is meant to be embedded in a widget, not a full-fledged recommendation platform across an entire music service.
—iTunes Genius. Sub-standard, algorithm only – developed in-house. Only uses iTunes data. Steve Jobs has creepy man crush on John Mayer and Jack Johnson.
—MySpace Music. Crazy flashing yellow buttons that randomly start playing Buffalo Springfield songs when you visit your friend’s page.
—AmazonMP3. Utilizes the Amazon recommendation platform which is based mainly on collaborative filtering. We assume they use some human tweaking, but they’ve never publicly stated this fact. The AmazonMP3 recommendations are crippled because they are based on regular Amazon recommendations which are very focused on closely related items (i.e. Bob Dylan’s _Blood on the Tracks_ returns Bob Dylan’s _Blonde on Blonde_. duh!)
—Last.fm. Purely algorithm-based utilizing only data from other members and their scrobbles.