recicon.gif

Way back in September 2003, we discussed the Napster Cooption Business Model. The basic premise was that:

“The industry had a golden opportunity to establish the “cooption model,” working with Napster as a centralized downloading center. This involved a jiu jitsu of the Napster sharing framework. The goal of the model would be to turn the Napster network into a massive data mining / advertising promotion / sales machine.

Each aspect of this model emphasizes the accumulation, analysis and application of consumer music data. The first goal would be to find out a) what people are listening to; b) what else they might want to listen to; and c) extending their relationships with the artists whose music they appreciate.

One of the best aspects of the Napster framework was user’s ability to peruse other people’s hard drives. Tracking downloading habits relative to that data could have been enormously powerful.”

This collaborative filtering methodology is seen in several other apps — notably, iRATE Radio (Music Business Model IV).

Now, a similar concept — “The Music Recommendation System” — is being developed by a coupla smart guys over at Department of Computer Science at the University of Illinois at Urbana-Champaign. The Senior Project (2003-2004) of Robert Chin, James Tuley and James Lottes (via Professor Ralph Johnson) is creating a collaborative filtering algorithm using iTune’s “own databases of song track information and user preferences provided by the client.”

Here’s their description:

“The Music Recommendation System is an automated system that provides music recommendations specifically tailored to each user to find new music that they might like. This system, designed by students at the University of Illinois (Champaign-Urbana), operates by taking ratings from your own iTunes playlists and comparing them against other users who have used the recommendation system. Right now we have a very small number of users, and so the recommendations will most likely be laughable. However they will get better over time as more people enter into the system; meanwhile, enjoy while the numbers grow. Download the client below and try it out. Tell your friends to try MRS to help improve the results.”

To learn more details, see About this Project…

Of course, algorithms such as this wouldn’t be necessary if there was not such a high degree of ownership concentration of U.S. radio stations; The narrow playlists all but eliminate the use of radio as a venue for discovering new music. A major source of falling music sales is the lack of any musical diversity — or even half decent song lists — on the radio, but that’s another issue entirely. But until U.S. radio is deconcentrated, this is a healthy move in the direction of a Non-Superstar Music Business model.

Category: Music

Please use the comments to demonstrate your own ignorance, unfamiliarity with empirical data and lack of respect for scientific knowledge. Be sure to create straw men and argue against things I have neither said nor implied. If you could repeat previously discredited memes or steer the conversation into irrelevant, off topic discussions, it would be appreciated. Lastly, kindly forgo all civility in your discourse . . . you are, after all, anonymous.

One Response to “Music Recommendation System”

  1. Magic Genie says:

    Also, check out the GenieLab music recommendation system: GenieLab.com.