Netflix Prize: Close, But No $1 Million Cigar

Source from:  bits.blogs.nytimes.com By Katie Hafner November 13, 2007 11/14/2007

Tags: AT&T Labs, collaborative filtering, netflix Maybe it's not so easy to improve recommendation software after all. In October 2006, Netflix, the online movie rental service, announced that it would award $1 million to the first person or team who could devise a system that is 10 percent more accurate than the company's current system for suggesting movies to customers. More than 27,000 contestants from 161 countries submitted their guesses. They got close, but not close enough. Today the company, based in Los Gatos, Calif., announced that it is awarding an annual progress prize of $50,000 to a group of researchers at AT&T Labs, who improved the current recommendation system by 8.43 percent. But the $1 million grand prize is still up for grabs. A $50,000 progress prize will be awarded every year until the 10 percent goal is met. Yehuda Koren, the leader of the AT&T Labs team, based in Florham Park, New Jersey, said he and his team spent 2,000 hours performing data analysis and computation. The race has remained close, with no consistent front-runner. The AT&T Labs team was often neck and neck with teams from the University of Toronto, Princeton University, and the Budapest University of Technology and Economics. Enditem