The Book of Trees is now available!      See other retailers
Home     About     VC Book     Stats     Blog     Books     Links     Contact  
Search the VC database:
    Others   < Prev | 29 of 77 | Next >
The materials shown on this page are copyright protected by
their authors and/or respective institutions.
Netflix Visualization
Author(s):
chef-ele
Institution:
(unknown)
Year:
2006
URL:
http://www.flickr.com/photos/chef_ele/sets/72157600111346295/
Project Description:
As part of the Netflix Prize competition, chef-ele has created a computer algorithm that can show different clusters of movies within the Netflix database. Chef-ele has used the open-source graph visualization package GUESS for most of his visualizations.

As he explains: "To generate those graphs I basically calculated the full movie-movie correlation matrix, using a straight Pearson correlation with Fisher confidence interval correction & a few other tweaks. Then my program writes a textfile of node & edge definitions, which GUESS reads in. Each movie is a node in the graph, with a label (movie title). The lines/edges connect each movie with the one most similar neighbor movie (in the Fisher/Pearson sense). (...) The graphs I did make show some very reasonable clusters. Some movies -- especially those in series & sequels -- have stronger / larger clusters (such as Friday the 13th sequels the 'Friends' TV series, everything Star-Trek related, etc). But clusters around 'themes' (kids movies, shoot-em-ups, etc.) were also found by the algorithm & seem pretty clear."

Comments (0):
*Note* Before you submit your comment, bear in mind there's no guarantee it will be seen by this project's author. In case you want to contact the author directly, please follow the provided URL.
Leave a Comment:
* COMMENTS HAVE BEEN TEMPORARILY DISABLED *
(We're looking for the best solution to avoid unwanted SPAM)
Manuel Lima | VisualComplexity.com