In October 2006, Netflix kicked off a M competition by releasing 100 million movie ratings as a training set to be used to build a better recommendation system for their on-line movie rental business. This landmark data set generated intense interest from the statistics and machine learning communities, and attracted entries from over 3000 teams from academia and industry. In this talk, I will review our team's experience analyzing this data and document our journey towards winning a share of the million dollar prize. Some of the surprising lessons include the role of ensembles (of models and teams) in the drive for the top spot, the power of matrix decomposition techniques, and the interplay between collaboration and competitiveness during the contest.