music discovery machines

Pitchfork

Take a minute and think about your 10 favorite albums of all time. How did you discover them? Maybe you made an impulse buy at the record store counter, or you found a tape in a rental car. But it's more likely that you heard most of them through your friends, or a glowing review in a magazine, or catching a hit on the radio, or because you were already following the catalog of a producer or label or artist. In other words, you got a recommendation. If you had the time, you could work your way through your record collection and explain how you made each purchase.

So how about predicting what you'll do next? Since the mid-1990s, online music recommendation or music discovery tools have studied our tastes and told us what to buy. And in the past year, several startups have launched with new, more ambitious software that someday may understand us better than we know ourselves.

The idea that a computer could judge music, let alone recommend it, strikes some as repugnant; yet many customers are drawn to the idea of finding records thanks to the Web's promise of perfect information. In the same way that your one true love could be working at a bank in Santa Fe, and the two of you may never meet, there are bands out there that would become your lifetime favorites-- if only someone would hand them to you.

[snip]

Music discovery tools could boost sales industry-wide-- as much as tenfold, depending on who you talk to-- and they're our best and, really, one of our only tools for tackling the marketing phenomenon known as the "Long Tail," where consumers wade through millions of niche and obscure albums thanks to the limitless shelves of online stores. Every day, bedroom musicians give away their Creative Commons-licensed mp3s, and digital distibutors snatch up forgotten back catalogs. San Francisco's IODA inked a deal to digitize 60,000 releases from China; how could any human wade through it all to find the best albums?

But how far can these tools go? Can they create maps of our sensibilities and tell us exactly what we want to hear-- night and day-- for any mood?

Read the whole article.
My last.fm page