I’ve just downloaded some freeware called Indy, which is a music discovery program that learns what you like, and plays more of it.

It works as a collaborative effort with many people online rating independent songs freely (and legally) available on the Internet.

The beauty comes in that it will learn what sort of music you like, based upon your responses to various tracks in relation to other people’s ratings, and over time should only serve up music that you’ll like.

How Indy Works
Indy uses an advanced collaborative filtering system to predict what kind of music you’ll enjoy hearing. As you rate songs, Indy finds out what you do and don’t like. It compares your preferences with the ratings of all the other Indy users. For example, if you rate a song highly, and another user also likes the same song, Indy guesses that you’d probably like other music that they enjoyed. As you rate more songs, Indy will gets better and better at picking songs that you’ll really enjoy.

I’ve only been using it for about an hour, so can’t comment on how effective its filtering is. It is serving up some interesting music, and I’ve added about 20 tracks to my iTunes folder already.

Each track includes a link to the artist’s website, so that you can find out more information, and ultimately buy more music, from those you like.

It will be interesting to see whether the iTunes Store stocks any music by the bands I’m downloading. That would be a cool link.

I’d imagine this service could get pretty tedious over dialup connections; at least a basic broadband makes the experience worthwhile. Clicking through songs quickly forces a reload from the server; playing them through in their entirity usually allows uninterrupted playback as new tracks are downloaded in the background.

I’ll repot back when I can tell what it’s learnt of my musical tastes.