(2 of 3)
The Netflix competition opened a window onto a world that's usually locked away deep in the bowels of corporate R&D departments. The eventual winner which clinched the prize last fall was a seven-man, four-country consortium called BellKor's Pragmatic Chaos, which included Bob Bell and Chris Volinsky, two members of AT&T's research division. Talking to them, you start to see how difficult it is to make a piece of software understand the vagaries of human taste. You also see how, oddly, software understands things about our taste in movies that a human video clerk never could.
The key point to grasp about collaborative-filtering software is that it knows absolutely nothing about movies. It has no preconceptions; it works entirely on the basis of the audience's reaction. So if a large enough group of people claim to have enjoyed, say, both Saw V and On Golden Pond, the software would be forced to infer that those two movies share some common quality that the viewers enjoyed. Crazy? Or crazy genius?
In such a case, the software would have discovered an aesthetic property that we might not even be aware of or have a name for but which in a mathematical sense must be said to exist. Even Bell and Volinsky don't always know what the properties are. "We might be able to describe them, or we might not be able to," Bell says. "They might be subtleties like 'action movies that don't have a lot of blood, don't have a lot of profanity but have a strong female lead.' Things like that, which you would never think to categorize on your own." As Volinsky puts it, "A lot of times, we don't come up with explanations that are explainable."
That makes recommendation engines sound practically psychic, but everyday experience tells us that they're actually pretty fallible. Everybody has felt the outrage that comes when a recommendation engine accuses one of a secret desire to watch Rocky IV, the one with Dolph Lundgren in it. In 2006, Walmart was charged with racism when its recommendation engine paired Planet of the Apes with a documentary about Martin Luther King. But generally speaking, the weak link in a recommendation engine isn't the software; it's us. Collaborative filtering works only as well as the data it has available, and humans produce noisy, low-quality data.
The problem is consistency: we're just not good at expressing our desires in rating form. We rate things differently after a bad day at work than we would if we were on vacation. Some people are naturally stingy with their stars; others are generous. We rate movies differently depending on whether we rate them right after watching them or if we wait a week, and differently again depending on whether we saw a lousy movie or a good movie in that intervening week. We even rate differently depending on whether we rate a whole batch of movies together or one at a time.
All this means that there's a ceiling to how accurate collaborative filtering can get. "There's a lot of randomness involved," Volinsky admits. "There's some intrinsic level of error associated with trying to predict human behavior."
The Great Choice Epidemic
Recommendation engines are a response to the strange new world of online retail. It's a world characterized by a surplus of something we usually can't get enough of: choice.
We're drowning in it. As Sheena Iyengar points out in her book The Art of Choosing, in 1994 there were 500,000 different consumer goods for sale in the U.S. Now Amazon alone offers 24 million. When faced with such an oversupply of choice, our little lizard brains go straight to vapor lock. "We think the profusion of possibilities must make it that much easier to find that perfect gift for a friend's birthday," Iyengar writes, "only to find ourselves paralyzed in the face of row upon row of potential presents." We're living through an epidemic of choice. We require an informational prosthesis to navigate it. The recommendation engine is that prosthesis: it winnows the millions of options down to a manageable handful.
But there's a trade-off involved. Recommendation engines introduce a new voice into the cultural conversation, one that speaks to us when we're at our most vulnerable, which is to say at the point of purchase. What is that voice saying? Recommendation engines aren't designed to give us what we want. They're designed to give us what they think we want, based on what we and other people like us have wanted in the past.
Which means they don't surprise us. They don't take us out of our comfort zone. A recommendation engine isn't the spouse who drags you to an art film you wouldn't have been caught dead at but then unexpectedly love. It won't force you to read the 18th century canon. It's no substitute for stumbling onto a great CD just because it has cool cover art. Recommendation engines are the enemy of serendipity and Great Books and the avant-garde. A 19th century recommendation engine would never have said, If you liked Monet, you'll love Van Gogh! Impressionism would have lasted forever.