Netflix awarded a $1 million prize to a developer team in 2009 for an algorithm that increased the accuracy of the company’s recommendation engine by 10 percent. But today it doesn’t use the million-dollar code, and has no plans to implement it in the future, Netflix announced on its blog Friday.
The post goes on to explain why: a combination of too much engineering effort for the results, and a shift from movie recommendations to the “next level” of personalization caused by the transition of the business from mailed DVDs to video streaming.
Netflix notes that it does still use two algorithms from the team that won the first Progress Prize for an 8.43 percent improvement.
via ars technica
It turns out that all the prize-winning work was perfect for DVD-by-mail where users add something to their queue and, best-case scenario, receive it the following day. But, now that instant streaming is taking over the parameters have changed. Viewers want something to watch immediately and like the option of flipping between several options.
That is why the Netflix updated all of its interfaces to show rows of movies giving you many, many options. It’s a subtle shift from finding the one movie you will love two days from now, to showing all the possible movies you might want to watch right now.
I guess that is the simplest way to put it, but if you want to know more the Netflix personalization science and engineering team, Xavier Amatriain and Justin Basilico, posted a lengthy and detailed, but interesting write-up, Beyond the 5 stars.