Your SlideShare is downloading. ×
0
Personalizing Netflix

    A brief history
            Jon Sanders
 Recommendation Systems Engineering
               Netf...
Fun facts about Netflix
World’s largest online movie rental service   #1 in customer satisfaction
Founded 1997            ...
In the beginning…




 Everyone sees the same site
Evolve methodically
The rating widget

•  Ask about & predict movie Enjoyment

•  User-similarity collaborative filter

•  Recommendations fue...
Score & sort any movie




Combine popularity & enjoyment prediction
Tune recommendations
•  Movie-similarity collaborative filter

•  K-nearest-neighbor algorithm

•  More credible connectio...
Interest-based discovery




Metadata connections: actor, director, genre, …
Ask about Interest




Moderate prominence of catalog areas
Ask other people




Community offers decision support
Explain why




Build trust with reflected evidence
$1M Netflix Prize
•  Improve accuracy of Enjoyment predictions
   –  100M ratings
   –  Achieve 10% better than Netflix RM...
A website for each subscriber
Evolution continues
•  Tailor with more metadata, implicit data
•  Streaming-specific personalization




•  Collaborative...
Links

•    http://jobs.netflix.com
•    http://www.netflix.com/ContactUs
•    http://www.netflixprize.com
•    http://www...
Upcoming SlideShare
Loading in...5
×

Jon Sanders on Collaborative Filters at SXSW

2,211

Published on

Jon Sanders of Netflix presenting "Collaborative Filters: The Evolution of Recommendation Engines" at SXSW Interactive, March 14 2009

Published in: Technology, Business

Transcript of "Jon Sanders on Collaborative Filters at SXSW"

  1. 1. Personalizing Netflix A brief history Jon Sanders Recommendation Systems Engineering Netflix Los Gatos, CA jsanders @ netflix.com http://jobs.netflix.com
  2. 2. Fun facts about Netflix World’s largest online movie rental service #1 in customer satisfaction Founded 1997 Video rental companies (Consumer Reports) Online retail (ForeSee) With more than… On an average day 10M subscribers, $1B revenue 2M DVDs shipped 100K DVD titles, 50 distribution centers 2M movie ratings received 12K streaming movies & TV episodes 1.5B minutes streamed to 1M Xbox360’s 2B movie ratings 60% of movies selected based on personalized recommendations Connecting people with movies they’ll love
  3. 3. In the beginning… Everyone sees the same site
  4. 4. Evolve methodically
  5. 5. The rating widget •  Ask about & predict movie Enjoyment •  User-similarity collaborative filter •  Recommendations fuel discovery
  6. 6. Score & sort any movie Combine popularity & enjoyment prediction
  7. 7. Tune recommendations •  Movie-similarity collaborative filter •  K-nearest-neighbor algorithm •  More credible connections
  8. 8. Interest-based discovery Metadata connections: actor, director, genre, …
  9. 9. Ask about Interest Moderate prominence of catalog areas
  10. 10. Ask other people Community offers decision support
  11. 11. Explain why Build trust with reflected evidence
  12. 12. $1M Netflix Prize •  Improve accuracy of Enjoyment predictions –  100M ratings –  Achieve 10% better than Netflix RMSE •  Innovative, engaged research community •  Highly relevant results –  Global and time-based corrections –  SVD, RBM models –  Blending predictors
  13. 13. A website for each subscriber
  14. 14. Evolution continues •  Tailor with more metadata, implicit data •  Streaming-specific personalization •  Collaborative Filtering is a component of personalization •  People want to drive, not be led •  Offer discovery, focus and decision support http://jobs.netflix.com
  15. 15. Links •  http://jobs.netflix.com •  http://www.netflix.com/ContactUs •  http://www.netflixprize.com •  http://www.netflix.com/netflixfindyourvoice •  http://en.wikipedia.org/wiki/Collaborative_filtering
  1. A particular slide catching your eye?

    Clipping is a handy way to collect important slides you want to go back to later.

×