Filed under: Community Building, Search Technology, Web 2.0, E-Commerce
I’ve probably discussed Netflix more than any other online business here, primarily because they have been a leader in using the power of online community and Web 2.0 in general to directly impact their customer experience. (See Netflix - A Different Approach, Netflix Using Community Intelligence, and many more Netflix posts.) Their savvy exploitation of crowd wisdom has helped Netflix earn top honors in Web customer satisfaction. One of the more interesting ways Netflix is tapping community savvy is with their effort to improve their recommendation algorithm. Katie Hafner of the New York Times details Netflix’s crowdsourcing effort is in Netflix Prize Still Awaits a Movie Seer.:
Last October, Netflix, the online movie rental service, announced that it would award $1 million to the first person or team who can devise a system that is 10 percent more accurate than the company’s current system for recommending movies that customers would like.
About 18,000 teams from more than 150 countries — using ideas from machine learning, neural networks, collaborative filtering and data mining — have submitted more than 12,000 sets of guesses. And the improvement level to Netflix’s rating system is now at 7.42 percent.
I’ve commented occasionally that the Netflix algorithm is a bit imperfect. The recommendations I receive are sometimes rather odd and off the mark, or are painfully pedestrian - yes, The Godfather is a movie I’d like, but I’ve seen it umpteen times. Some of the seemingly odd recommendations, of course, may be exactly what I’m looking for - by analyzing the likes of similar customers, they can recommend something I’d never choose on my own. Still, I find I don’t act on their recommendations all that often, though I do look at their community star ratings whenever I check out an unfamiliar title. So, I’m happy that Netflix is trying new approaches… actually, thousands of new approaches.
That the contest has generated such intense interest and competition is an impressive testament to the value of crowdsourcing. Netflix could have dedicated a million dollars to hiring a few PhDs and funding a research effort for a year, but I find it highly unlikely that such an effort would have produced anything resembling the variety of approaches tested so far or an equivalent percentage improvement. And it’s entirely possible that nobody will hit the 10% target, and Netflix will get some great new algorithmic approaches for a fraction of the million dollar prize. (The award for the best improvement if the target isn’t hit is a mere $50,000; this amount will be awarded annually until the target is hit.)
Add this post to: del.icio.us - Digg it - Stumble it - Furl - Yahoo MyWeb No Comments so far
Leave a comment
Leave a comment
Line and paragraph breaks automatic, e-mail address never displayed, HTML allowed:
<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <code> <em> <i> <strike> <strong>