It took them three years, but a team led by AT&T Research engineers won the $1 million Netflix Prize for devising the best way to improve the company’s movie recommendation algorithm, which generates an average of 30 billion predictions per day, by 10 percent or more.
Amazingly, the decision came down to a matter of minutes, according to Netflix Prize chief Neil Hunt. BellKor’s Pragmatic Chaos submitted their solution 10 minutes earlier than the second-place team, The Ensemble, while the two teams’ algorithms were a perfect tie, score-wise.