NetFlix Announces Winner Of Movie Recommendation Algorithm Contest

by Jason Wilk on September 21, 2009

  • In October 2006 NetFlix announced a $1M contest for anyone that could come up with a recommendation software that could do at least a 10% better job accurately predicting the movies customers would like than Netflix’s in-house software, Cinematch.
  • The winner, formally announced today, 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 front runner in the contest, and in late June it finally surpassed the 10 percent barrier. The BellKor team presented its final submission 20 minutes before the deadline. Just before time ran out, The Ensemble (another contestant) 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. The extra 20 minutes cost The Ensemble $1 million dollars.
  • The new recommendation system couldn’t have been achieved by their in-house team and outsourcing the development would have cost well over $1M. Now the leader of mail-in movie rentals will better be able to match you with the movies that you might be interested in; a key ingredient in getting consumers to continuing subscribing. NetFlix said the contest was so successful that they are going to do it again with a new prize for the team that can create individual consumer ‘taste profiles’. Why do we even need employees when we could just set a contest for every benchmark?

Leave a Comment

Previous post:

Next post: