Netflix in 2006 held an open competition to find the collaborative filtering algorithm that would best predict whether or not a user would like a particular film or TV show based on previous ratings. The grand prize of $1 million was awarded to a team called “BellKor’s Pragmatic Chaos” in 2009. The team’s algorithm was found to be 10% more effect than Netflix’s own recommendation service, however the company never implemented the team’s solution into its own service. “We evaluated some of the new methods offline but the additional accuracy gains that we measured did not seem to justify the engineering effort needed to bring them into a production environment,” Netflix finally explained in a recent blog post. “Also, our focus on improving Netflix personalization had shifted to the next level by then.” The company said because the majority its users were streaming videos rather than renting DVDs, it wasn’t logical to integrate the algorithm into its recommendation service, which is different for its streaming service and DVD rental program.