Steve Krause takes a thorough look at music recommendation systems Pandora and Last.fm. I’ve written about both before, but Steve goes a lot deeper and really plumbs the depths of the Nature vs. Nurture aspects of the two services.
Give Pandora an artist or song, and it will find similar music in terms of melody, harmony, lyrics, orchestration, vocal character and so on. Pandora likes to call these musical attributes “genes” and its database of songs, classified against hundreds of such attributes, the “Music Genome Project.” On the nurture side (as in, it’s all about the people around you), Last.fm is a social recommender. It knows little about songs’ inherent qualities. It just assumes that if you and a group of other people enjoy many of the same artists, you will probably enjoy other artists popular with that group.
The parallel to the dating space is clear, personality testing vs. social recommendation engines. I had high hopes for Engage, a company I worked with last year which leverages a matchmaking community over tests and search engines, but I’m not seeing as big a take rate as I had expected. That doesn’t mean the concept doesn’t work, lack up traction could be related to myriad issues, from marketing to funding to management. Maybe someone from Engage will comment and share what’s happening there.
Technorati Tags: engage
