HowComputersKnowWhatWeWant BeforeWeDo.docx

1、HowComputersKnowWhatWeWant BeforeWeDoHow Computers Know What We Want - Before We DoHeres an experiment: try thinking of a song not as a song but as a collection of distinct musical attributes. Maybe the song has political lyrics. That would be an attribute. Maybe it has a police siren in it, or a pr

2、ominent banjo part, or paired vocal harmony, or punk roots. Any one of those would be an attribute. A song can have as many as 400 attributes - those are just a few of the ones filed under p.This curious idea originated with Tim Westergren, one of the founders of an Internet radio service based in O

3、akland, Calif., called Pandora. Every time a new song comes out, someone on Pandoras staff - a specially trained musician or musicologist - goes through a list of possible attributes and assigns the song a numerical rating for each one. Analyzing a song takes about 20 minutes.The people at Pandora -

4、 no relation to the alien planet - analyze 10,000 songs a month. Theyve been doing it for 10 years now, and so far they ve amassed a database containing detailed profiles of 740,000 different songs. Westergren calls this database the Music Genome Project.There is a point to all this, apart from sett

5、ling bar bets about which song has the most prominent banjo part ever. The purpose of the Music Genome Project is to make predictions about what kind of music youre going to like next. Pandora uses the Music Genome Project to power what s known in the business as a recommendation engine: one of thos

6、e pieces of software that gives you advice about what you might enjoy listening to or watching or reading next, based on what you just listened to or watched or read. Tell Pandora you like Spoon and itll play you Modest Mouse. Tell it you like Cajun accordion virtuoso Alphonse“Bois Sec”Ardoin and it

7、ll try you out on some Iry LeJeune. Enough people like telling Pandora what they like that the service adds 2.5 million new users a month.Over the past decade, recommendation engines have become quietly ubiquitous. At the appropriate moment - generally when you re about to consummate a retail purcha

8、se - they appear at your shoulder, whispering suggestively in your ear. Amazon was the pioneer of automated recommendations, but Netflix, Apple, YouTube and TiVo have them too. In the music space alone, Pandora has dozens of competitors. A good recommendation engine is worth a lot of money. Accordin

9、g to a report by industry analyst Forrester, one-third of customers who notice recommendations on an e-commerce site wind up buying something based on them.The trouble with recommendation engines is that theyre really hard to build. They look simple on the outside - if you liked X, youll love Y! - b

10、ut they re actually doing something fiendishly complex. Theyre processing astounding quantities of data and doing so with seriously high-level math. Thats because theyre attempting to second-guess a mysterious, perverse and profoundly human form of behavior: the personal response to a work of art. T

11、heyre trying to reverse-engineer the soul. Theyre also changing the way our culture works. We used to learn about new works of art from friends and critics and video-store clerks - from people, in other words. Now we learn about them from software. Theres a new class of tastemakers, and theyre not h

12、uman. Learning to Love Dolph LundgrenPandora makes recommendations the same way people do, more or less: by knowing something about the music its recommending and something about your musical taste. But thats actually pretty unusual. It sa very labor-intensive approach. Most recommendation engines w

13、ork backward instead, using information that comes not from the art but from its audience.It sa technique called collaborative filtering, and it works on the principle that the behavior of a lot of people can be used to make educated guesses about the behavior of a single individual. Heres the idea:

14、 if, statistically speaking, most people who liked the first Sex and the City movie also likeMamma Mia! , then if we know that a particular individual liked Sex and the City, we can make an educated guess that that individual will also like Mamma Mia!It sounds simple enough, but the closer you look,

15、 the weirder and more complicated it gets. Take Netflixs recommendation engine, which it has dubbed Cinematch. The algorithmic guts of a recommendation engine are usually a fiercely guarded trade secret, but in 2006 Netflix decided it wasnt completely happy with Cinematch, and it took an unusual app

16、roach to solving the problem. The company made public a portion of its database of movie ratings - around 100 million of them - and offered a prize of $1 million to anybody who could improve its engine by 10%. The Netflix competition opened a window onto a world that s usually locked away deep in th

17、e bowels of corporate R&D departments. The eventual winner - which clinched the prize last fall - was a seven-man, four-country consortium called BellKors Pragmatic Chaos, which included Bob Bell and Chris Volinsky, two members of AT&Ts research division. Talking to them, you start to see how diffic

18、ult 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 mo

19、vies. It has no preconceptions; it works entirely on the basis of the audiences reaction. So if a large enough group of people claim to have enjoyed, say, bothSaw Vand On Golden Pond, the software would be forced to infer that those two movies share some common quality that the viewers enjoyed. Craz

20、y? 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 dont always know what the properties are. “We might be able to describe th

21、em, or we might not be able to, ”Bell says.“They might be subtleties like action movies that dont have a lot of blood, dont 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 co

22、me up with explanations that are explainable.”That makes recommendation engines sound practically psychic, but everyday experience tells us that theyre actually pretty fallible. Everybody has felt the outrage that comes when a recommendation engine accuses one of a secret desire to watchRocky IV, th

23、e one with Dolph Lundgren in it. In 2006, Walmart was charged with racism when its recommendation engine paired Planet of the Apeswith a documentary about Martin Luther King. But generally speaking, the weak link in a recommendation engine isnt the software; it sus. Collaborative filtering works onl

24、y as well as the data it has available, and humans produce noisy, low-quality data.The problem is consistency: were 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 t

25、heir 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 rat

26、e a whole batch of movies together or one at a time.All this means that theres a ceiling to how accurate collaborative filtering can get. “Theres a lot of randomness involved,”Volinsky admits. “Theres some intrinsic level of error associated with trying to predict human behavior.”The Great Choice Ep

27、idemicRecommendation engines are a response to the strange new world of online retail. It s a world characterized by a surplus of something we usually cant get enough of: choice.Were drowning in it. As Sheena Iyengar points out in her bookThe Art of Choosing, in 1994 there were 500,000 different con

28、sumer 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 wri

29、tes, “only to find ourselves paralyzed in the face of row upon row of potential presents. ”Were 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.B

30、ut theres a trade-off involved. Recommendation engines introduce a new voice into the cultural conversation, one that speaks to us when were at our most vulnerable, which is to say at the point of purchase. What is that voice saying? Recommendation engines arent designed to give us what we want. The

31、yre 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 dont surprise us. They dont take us out of our comfort zone. A recommendation engine isnt the spouse who drags you to an art film you wouldn t have been caught dead at

32、but then unexpectedly love. It wont force you to read the 18th century canon. Its 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, youll love Van Gogh! Impressionism would have lasted forever.The risk you run with recommendation engines is that theyll keep you in a rut. They do that because ruts are comfy places - though often theyre deeper than they look. “By definition, we keep you in the sam