George Dahl: Machine Learning for March Madness

This paper (referenced in the post) is also relevant. The application is to NBA basketball:<p>"Incorporating Side Information into Probabilistic Matrix Factorization Using Gaussian Processes." Ryan Prescott Adams, George E. Dahl, and Iain Murray. In Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, 2010.<p>Paper: <a href="http://www.cs.toronto.edu/~gdahl/papers/dpmfNBA.pdf" rel="nofollow">http://www.cs.toronto.edu/~gdahl/papers/dpmfNBA.pdf</a><p>Code: <a href="http://www.cs.toronto.edu/~rpa/code/dpmf-nba.tgz" rel="nofollow">http://www.cs.toronto.edu/~rpa/code/dpmf-nba.tgz</a>

He has some good points. I like the one about correlations between team scores potentially distorting the strength of offenses and defenses in a naive model.