The crazy way Netflix recommends and categorizes movies

vbimport

#1

The crazy way Netflix recommends and categorizes movies.

[newsimage]http://static.rankone.nl/images_posts/2012/03/y0L8Wl.jpg[/newsimage]Netflix has made it a goal to cater to streaming subscribers with content recommendations. But how does the company arrive at its conclusions? According to Todd Yellin, Netflix vice president of product innovation, it isn't magic. And it isn't perfect, either.


Read the full article here: [http://www.myce.com/news/the-crazy-way-netflix-recommends-and-categorizes-movies-60528/](http://www.myce.com/news/the-crazy-way-netflix-recommends-and-categorizes-movies-60528/)


Please note that the reactions from the complete site will be synched below.

#2

How is that crazy? it’s dead obvious to me.

  1. Ask people what they like.
  2. Tag movies according to content
  3. if they have hired movies previously, factor their preference into the recommendation.
    3b) if they have provided positive feedback, give higher ranking to those tags.

it’s not just highly obvious, it would also be excessively easy.
I could program the algorithm, and I’m not even a programmer.

The real problem is programming access to the various databases & etc/etc.

I’m still scratching my head about why the title says “Crazy way”.