MySpace Opens Up Recommendation Engine

    September 16, 2009
    Chris Crum

MySpace has announced an open source framework for "distributed computation," which is ultimately a recommendation engine. It’s called Qizmt, and it’s the feature the social network currently uses for its "People you may Know" feature.

"Qizmt can be used for many operations that require processing large amounts of data such as collaborative filtering for recommendations and analytics," explains MySpace COO Mike Jones.

Qizmit’s developer environment lets developers code in a "familiar setting," and the SQL interface allows for scripting against Qizmt.



MySpace has published the Qizmt code for developers to download and start contributing to. In addition, they have open sourced their MSFast, which is the company’s technology  that lets developers track page load performance and user experience data. Features of this include:

  • Measure the CPU hit and memory footprint of your pages as they render on the client’s browser
  • Review screen shots of the page while it renders
  • Review the rendered HTML on each point of the page’s lifecycle
  • Measure and show estimates of the time it takes to render each section of the page in different connection speeds
  • Validate the content of your page against a set of proven “best practice” rules of web development
  • Review downloaded files and show download time estimation on different bandwidths

MySpace is set to demonstrate Qizmt at the ComputerWorld Business Intelligence Perspectives conference taking place in Chicago today.