The Netflix Prize contest is officially over. One month ago BellKor's Pragmatic Chaos made a submission with a 10.05% improvement over Cinematch. The contest ends 30 days after any submission over 10%. Yesterday a new team called The Ensemble made a submission at 10.09% accuracy (a 0.01% improvement over BellKor's Pragmatic Chaos). Today, 24 minutes before the contest finished BellKor's Pragmatic Chaos made a submission of 10.09%. Four minutes before the end The Ensemble made their final submission with a 10.10% improvement. Both of these teams were actually a combination of many smaller teams. In the end the key to victory was combining the results of a myriad of different algorithms/approaches.
Now that the Netflix Prize has finished I will start focusing on a new contest ☺. Eternity II is a puzzle with a two million dollar prize. I have written a solver using stochastic local search. My solution currently has a score of 437 out of 480. Last year the highest score was 467 (with a $10,000 prize).
1 comment:
I am "concerned" the combined teams circumvented the "one sumbmission a day" netflix requirement, whose intention was not to overfit the data, ie to win on merit, general power and innovation, not on reverse-engineering the dataset. It looks like having access to the individual submission "trained vectors" may have been enough of a covert dataset signal to win.
Post a Comment