research intern
I worked as a research intern for
MusicStrands
in the summer of 2005. During this time I developed a novel method for visualizing the relationships between songs based on how people are arranging them on playlists of mp3's.
I called this method "Music Mapping", based on the notion that they could serve as a method for exploring new music, based on music that an individual already owns. I put together a
small movie that explains the results of one such map (the movie file is large... use "right-click, download as" to view). This project proved to be very successful, and I was given the opportunity to present the results at a Stanford data mining course as well as at the Music 2.0 Conference (another link).
Recently I've applied these same music mapping techniques as a tool for exploring musical recommendations. The tool is available online here. You can either browse through a demo map, or log on to your MyStrands account and upload playlists using the Discovery Client or the web. The service will allow you to map these playlists and browse through the results.