As promised earlier this month, Netflix today announced the winner of its $1 million prize for the tech team that could improve the online DVD rental company’s customer recommendation system by 10 percent.
From the New York Times:
The winner, formally announced Monday morning, is a seven-person team of statisticians, machine-learning experts and computer engineers from the United States, Austria, Canada and Israel. The multinational team calls itself BellKor’s Pragmatic Chaos. The group — a merger of teams — was the longtime frontrunner in the contest, and in late June it finally surpassed the 10 percent barrier. Under the rules of the contest, that set off a 30-day period in which other teams could try to beat them.
However, as the Times explains, the results couldn’t have been closer. In fact, Netflix had to turn to the fine print to choose a winner:
The BellKor team presented its final submission 20 minutes before the deadline, [Netflix CEO Reed] Hastings said. Then, just before time ran out, [runner-up] The Ensemble made its last entry. The two were a dead tie, mathematically. But under contest rules, when there is a tie, the first team past the post wins.
That’s like deciding a Super Bowl on which team came through the tunnel first! (OK, maybe not exactly.) But rules are rules, and BellKor comes away with the big prize in the three-year competition.
Netflix previously announced it was sponsoring another $1 million contest, the details of which were laid out today. It will ask teams to use data sets to model the “taste profiles” of Netflix customers based on demographic information and history of DVD choices.