Should We Care About Content? Recommending by Proxy with Big Metadata

77cacd503a0b6641e3b7a2e26dbbbaa1?s=47 Ben Fields
October 01, 2012

Should We Care About Content? Recommending by Proxy with Big Metadata

When constructing a music recommender system, which is more important: a musicological understanding of the catalog of music in a system or the number of times two particular songs were played one after the other and were `liked’? Even better, if a system knows the latter, does the former even matter? Do machines that predict behavior need to learn to listen? Or is observing behavior enough?

77cacd503a0b6641e3b7a2e26dbbbaa1?s=128

Ben Fields

October 01, 2012
Tweet

Transcript

  1. 1.

    Should we care about content? Recommending by proxy with big

    metadata B e n F i e l d s @ a l s o t h i n g s
  2. 2.
  3. 8.
  4. 16.
  5. 26.
  6. 39.
  7. 40.
  8. 42.

    Netflix Prize 500K people’s ratings of 18k movies Take these

    and predict the ratings of movies that haven’t been Rated
  9. 43.
  10. 46.

    No.

  11. 48.

    Million Song Dataset challenge (kaggle) The partial listening history of

    1M people Predict the tracks that are missing
  12. 51.

    No.

  13. 52.

    so?

  14. 54.

    Simple use of metadata from far and wide gets you

    further than Deep understanding of core-data