Netflix's Million-Dollar Quest for Good Movie Tips
A year ago, the online movie rental company Netflix offered $1 million to anyone who could come up with a way to improve its movie recommendations by 10 percent. Nobody has earned the money, but a team from AT&T Labs came close.
And other online retailers are watching the online video rental company closely, looking to improve their own shopping recommendations.
With 7 million subscribers, Netflix does provide computerized recommendations. Customers rate movies on a scale of one to five stars. And Vice President Jim Bennett says the company's track record is pretty good.
"We get basically three out of four correct, within half a star," Bennett said. "Which is pretty high, actually."
Netflix uses what computer scientists call a "neighborhood approach."
"So if you rated Gone with the Wind and Anna Karenina both positively, and we find many people who have done that, then we find a correlation between those two," Bennett said.
"So that if someone comes along and rates Gone with the Wind, but hasn't told us anything about Anna Karenina, we should adjust their prediction for Anna Karenina positively."
But the Netflix system only goes so far. Tens of thousands of statisticians and computer scientists have been working to improve it. No one scored the 10 percent improvement needed to claim the million-dollar grand prize. But the team from AT&T Labs came close.
By slicing and dicing millions of Netflix ratings, the team was able to find patterns that seem to suggest common factors that might lead certain customers to like certain films.
The factors behind the patterns could be dialogue or action or popular stars. But the team doesn't pretend to know. Statistician Bob Bell says he's not even much of a film buff. What interests him is the data.
"As far as we were concerned, the movies were just an ID number," Bell said. Netflix has awarded his team a "progress prize" for its work — and urged them to keep at it.
But if Bell's approach seems a little too mathematical, you might want to try another movie recommendation site, What To Rent (whattorent.com). One of the company's founders, Adam Geitgey, says the site asks would-be renters a series of personal questions, sort of like a matchmaker about to arrange a blind date.
"People relate to movies like they relate to people," Geitgey said. "If we can figure out what kind of person you are and what kind of person the movie would be, we can match you with a movie."
But that's not really practical on a large scale. Netflix Vice President Bennett says the beauty of his company's algorithm is that it can work automatically, and with any kind of product. That's why not only Netflix but all kinds of e-commerce sites are anxious to see it work better.
And recommendation algorithms aren't just good for companies that want to move more merchandise. Computer scientist John Riedl of the University of Minnesota says they are also good for customers who may be looking to find an out-of-the-way film that wasn't a blockbuster hit.
"What I'm excited about in recommenders is the possibility of letting the little hit matter," Riedl said, "for letting all of us who have our own quirky, special little movie or book taste be recommenders for people who like the kinds of things we recommend."
If Riedl is right, moviegoers and other online merchants could be giving Netflix's new and improved algorithm millions of thumbs up.
9(MDAyNzUwMDI2MDEyNTA3MTU5NzcyNTQyNA004))
RENEE MONTAGNE, host:
On Mondays, we talk about technology. And today the online rental company Netflix is trying to improve its recommended movies. A year ago, Netflix offered $1 million to anyone who could improve its high-technology movie referral system by 10 percent. No one's met that target quite yet, but today Netflix will award a $50,000 progress prize to the team that came the closest.
NPR's Scott Horsley takes a look.
SCOTT HORSLEY: When it comes to renting movies, Kensington Video in San Diego does it the old-fashioned way. There's not a computer in sight. Customers looking for recommendations turned to real people like Pam Cisneros.
Ms. PAM CISNEROS (Owner, Kensington Video): You know, I have a little lady coming earlier today, and she wanted another really good recommendation. Well, I know she doesn't like something that has lots of sex in it and something that's too brutal, as far as the violence goes - just a good movie without all that had extra stuff in there. They do make a few of those still.
HORSLEY: Netflix can't exactly duplicate that kind of personal attention with seven million subscribers, but the online rental company does provide computerized recommendations. Customers rate movies on a scale of one to five stars.
Vice President Jim Bennett says the company's track record is pretty good.
Mr. JAMES BENNETT (Vice President, Netflix): We get, basically, three out four correct, within a half of a star - which is pretty high, actually.
HORSLEY: Netflix uses what computer scientists call a neighborhood approach.
Mr. BENNETT: So if you rated "Gone with the Wind" and you rated "Anna Karenina" both positively, and we find many people who have done that, then we're able to find a correlation between those two, so that if somebody comes along and rates "Gone with the Wind" but hasn't told us anything about "Anna Karenina," we should adjust their prediction for "Anna Karenina" positively.
HORSLEY: But the Netflix system only goes so far. Thousands of statisticians and computer scientists have been competing to improve it. No one scored the 10 percent improvement needed to claim the million dollar prize.
But a team from AT&T Labs came close. By slicing and dicing millions of Netflix's ratings, the team was able to find patterns that seemed to suggest common factors that might lead certain customers to like certain films. Those factors could be dialogue or action or popular stars, but the team doesn't pretend to know.
Statistician Bob Bell says he's not even much a film buff. What interests him is the data.
Dr. BOB BELL (Statistician, AT&T Labs): As far as we were concerned, the movies were just an ID number.
HORSLEY: If that seems a little too mathematical, you might want to try another movie recommendation site: whattorent.com. Adam Geitgey says that site asked would-be runners a series of personal questions, sort of like a matchmaker about to arrange a blind date.
Mr. ADAM GEITGEY (Founder, Whattorent.com): People relate to movies like they relate to people, so then if we can figure out what kind of person you are and what kind of person the movie would be, we could match you with a movie.
HORSLEY: But that's not really practical on a large scale. Netflix Vice President Bennett says the beauty of his company's algorithm them is it can work automatically, and with any kind of product. That's why not only Netflix, but all kinds of e-commerce sites are anxious to see it work better.
Mr. BENNETT: It's our "Who Wants to be a Millionaire for Geeks." We're looking forward to giving out that million-dollar prize and getting that a little bit of extra accuracy that could make all the difference for our business.
HORSLEY: And recommendation algorithms aren't just good for companies that want to move more merchandise. Computer scientist John Riedl of the University of Minnesota argues they're also good for customers looking to find that out-of-the-way film that isn't a blockbuster hit.
Dr. JOHN RIEDL (Computer Scientist, University of Minnesota): What I'm excited about in recommenders is the possibility for letting the little hit matter, right? For letting all of us who have our own quirky, special little movie or book taste be recommenders for the people who like the kinds of things that we recommend.
HORSLEY: If Riedl's right, moviegoers and other online merchants could be giving Netflix's new and improved algorithm millions of thumbs up.
Scott Horsley, NPR News. Transcript provided by NPR, Copyright National Public Radio.
