I started working on the Netflix Prize in October 2007 in order to learn more about Machine Learning. I studied Physics, Math, and CS at the University of Massachusetts Amherst.
My method involves SVD (mf, nnmf, etc.), kNN, and a variety of neural network based approaches. I combine many results for my 8.31% score; the best individual result with a score achieves a score of 5.14% on the probe set.
I have not participated substantively in the contest since March 2008, at which point I was in fifth place.
Helpful References
Restricted Boltzmann Machines for Collaborative Filtering by Ruslan Salakhutdinov, Andriy Mnih, and Geoffrey Hinton of the ML@UToronto team.
Scalable Collaborative Filtering with Jointly Derived Neighborhood Interpolation Weights by Bob Bell, Yehuda Koren, and Chris Volinsky of the BellKor team.
Textbook: Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig
