Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!


Forgot your password?
Programming Math The Internet IT Technology

Psychologist Beating Math Nerds in Race to Netflix Prize 205

s1d writes "An almost-anonymous British psychologist named Gavin Potter has suddenly risen to the top of the Netflix prize charts. With his very first attempt, he got a score which took the BellKor team seven months to reach. Currently at a score of 8.07, he has only five teams ahead of him now in the race for the ultimate Netflix algorithm. 'Potter says his anonymity is mostly accidental. He started that way and didn't come out into the open until after Wired found him. "I guess I didn't think it was worth putting up a link until I had got somewhere," he says, adding that he'd been seriously posting under the name of his venture capital and consulting firm, Mathematical Capital, for two months before launching "Just a guy." When he started competing, he posted to his blog: "Decided to take the Netflix Prize seriously. Looks kind of fun. Not sure where I will get to as I am not an academic or a mathematician. However, being an unemployed psychologist I do have a bit of time."'"
This discussion has been archived. No new comments can be posted.

Psychologist Beating Math Nerds in Race to Netflix Prize

Comments Filter:
  • by Anonymous Coward on Tuesday March 04, 2008 @11:22PM (#22645744)
    5th place is not winning. Are you guys Ron Paul supporters too?
    • by glyph42 ( 315631 )
      Currently at 8th place. I've seen this story all over and I don't know why it does not link to the actual standings: http://www.netflixprize.com/leaderboard [netflixprize.com] Oh wait, I know why. Because it makes the story look dated!
  • Domain Knowledge (Score:5, Insightful)

    by Anonymous Coward on Tuesday March 04, 2008 @11:27PM (#22645772)
    It's called domain knowledge people. It helps being a psychologist when you're write a program reacting to people's behavior. If programmers knew how to do that, they would get laid more.
    • Re: (Score:3, Interesting)

      by Yold ( 473518 )
      Exactly what I thought, even if he is beating math-nerds, you cannot create a machine-learning algorithm without using fairly sophisticated mathematics. Since psychology is largerly based on statistics, I am sure the guy has a firm grounding in the subject. I am sure he isn't basing his algorithm on Aedipus Complexes (sic) and ink blots.
      • Re: (Score:2, Interesting)

        by droptone ( 798379 )
        You'd be surprised how many people in psychology are math-phobic and really only know the basic stuff they need to do research (z tests, t tests, ANOVA, regression, power for grant requests, etc) without any deeper understanding of the underlying concepts. If the guy went through a decent quantitative program then he'd have a much better understanding of math since they usually prefer the applicants to have several levels of calculus plus a handful of actual statistics courses (and not stat for psyc), along
  • What's the point? (Score:5, Interesting)

    by causality ( 777677 ) on Tuesday March 04, 2008 @11:28PM (#22645782)
    Is there some merit to this story other than "your sterotypes can be wrong", which is itself cliche enough to be considered a stereotype in its own right? I like Henry David Thoreau's explanation of such trivia:

    And I am sure that I never read any memorable news in a newspaper. If we read of one man robbed, or murdered, or killed by accident, or one house burned, or one vessel wrecked, or one steamboat blown up, or one cow run over on the Western Railroad, or one mad dog killed, or one lot of grasshoppers in the winter -- we never need read of another. One is enough. If you are acquainted with the principle, what do you care for a myriad instances and applications? To a philosopher all news, as it is called, is gossip, and they who edit and read it are old women over their tea. Yet not a few are greedy after this gossip. There was such a rush, as I hear, the other day at one of the offices to learn the foreign news by the last arrival, that several large squares of plate glass belonging to the establishment were broken by the pressure -- news which I seriously think a ready wit might write a twelve-month, or twelve years, beforehand with sufficient accuracy.

    And yes, I have karma to burn. Yes I do.
    • If we read of one man robbed, or murdered, or killed by accident, or one house burned, or one vessel wrecked, or one steamboat blown up, or one cow run over on the Western Railroad, or one mad dog killed, or one lot of grasshoppers in the winter -- we never need read of another.

      Right. Unless it's your brother that was robbed, your mother's house that burned, your life savings tied up in the boat that sank, your cow that was run down, or your new neighbor's rabid dog that needs killing.
      • Re: (Score:2, Funny)

        by 0123456789 ( 467085 )

        Right. Unless it's your brother that was robbed, your mother's house that burned.

        If you don't find out about those until you read about them in the newspaper, your family qualifies as dysfunctional. Really dysfunctional.

      • by besalope ( 1186101 ) on Wednesday March 05, 2008 @01:46AM (#22646518)

        Right. Unless it's your brother that was robbed, your mother's house that burned, your life savings tied up in the boat that sank, your cow that was run down, or your new neighbor's rabid dog that needs killing.
        Meh, that just sounds like the making of a country music hit.
  • Average psychologist (Score:5, Informative)

    by Anonymous Coward on Tuesday March 04, 2008 @11:31PM (#22645808)

    that had an undergraduate degree in psychology, a masters degree in operations research [wikipedia.org] that after being well employed for a number of years -- "In 2006, he left his job at IBM to explore the idea of starting a PhD in machine learning, a field in which he has no formal training. When he read about the Netflix Prize, he decided to give it a shot -- what better way to find out just how serious about the topic he really was?"

    • And he lives in what looks like a smart house in Central London - as we say in this country "he ain't short of a bob or two". No wonder his primary motivation isn't the $1m.
  • Very few psych majors do psych professional.

    I have a BA from U. of Houston, which I have used to do tech support and sales for a software company, and developed my own FPS as a solo project.
    • That's true (Score:5, Interesting)

      by Crazy Taco ( 1083423 ) on Tuesday March 04, 2008 @11:56PM (#22645950)

      Very few psych majors do psych professional. I have a BA from U. of Houston, which I have used to do tech support and sales for a software company, and developed my own FPS as a solo project.

      I've also found this to be true. Lol, I actually knew people in college that did nothing but program computers in their spare time, and took psych because it was easy, wouldn't distract them and gave them more time to do the programming they wanted. They didn't ever expect to practice psych.

    • Undergrad is the new high school.
  • Misleading summary (Score:5, Informative)

    by Zen Programmer ( 518532 ) on Tuesday March 04, 2008 @11:40PM (#22645856)
    The summary makes 2 references to Gavin Potter being a psychologist, but it ignores the part of the article that notes he has a master's degree in operations research. This is very much an OR problem. Still, it is impressive that he has been able to do as well as he has considering his competition. Good luck to him!
    • Re: (Score:3, Funny)

      by Red Flayer ( 890720 )

      This is very much an OR problem.
      I'm not so sure about that. Seems to me like the Netflix algorithm probably needs some ANDs and NOTs, and maybe even some IF...THENs.

      Not to mention that it likely can't be reduced to Boolean logic.

  • by oceaniv ( 1243854 ) on Tuesday March 04, 2008 @11:41PM (#22645866)
    The topic is incredibly fascinating. And just a thought, up to 5 centuries ago "scientists" were incredibly versatile people, with mastery over a few fields at a time... A lot of people argue that this was out of necessity, but could the versatility have been important development of multiple renaissances (In Greece, East/West Asia, and Europe)? And could the bottleneck specialization of fields that has occurred in the past three centuries simply be period of transition/stifling new ways of thinking? Could the emergence interdisciplinary experts lead to another 'renaissance' of sorts?
    • by Metasquares ( 555685 ) <slashdot@nospAM.metasquared.com> on Wednesday March 05, 2008 @12:02AM (#22645988) Homepage
      I think so [projectpolymath.org].
    • by Kenshin ( 43036 ) <kenshinNO@SPAMlunarworks.ca> on Wednesday March 05, 2008 @12:10AM (#22646034) Homepage
      See, I hate this current mode of profession.

      I work for a small company. My current job isn't stable, and doesn't pay well, so I'm taking an IT course so I can land a (hopefully) stable job/career.

      However... in my current job I wear all kinds of hats. Server's down? I'll fix it. Marketing materials need to be designed? I'll do it. Proposal needs to be edited? I'm there. Computer needs more RAM? I'll install it. Photo of product needs to be masked-out? Done. Need to do some research? I'll get on it.

      The kind of job I'm being trained for... I'll be stuck on the straight and narrow, handling one sort of task. When companies want an IT guy, they want an IT guy. I don't know how I'll be able to handle that. I LIKE having different responsibilities. I don't want to be one guy on an org chart with a specified duty.

      Blah. I really went on a tangent there...
      • I like being jack-of-all-trades too. But I'm finding that one must tread very carefully on this path.

        If you aren't careful, you end up being the fall guy for a widening array of mishaps.

        For instance, you help set up the video projector a couple of times for presentations. Then during the next presentation the projector fails. In some eyes it will be your fault, because you're now the "PowerPoint Guy." Nevermind that the bulb was past its recommended use hours, or that the presenter forgot his VGA dongle, or whatever.

        It seems like if I want to come out as the go-to guy for some area of tech, I'd damn well better get up to pro-level speed really quick. Because soon I'm going to have to be mitigating crises and solving complex problems that before were just chalked up to "well, that thing's always been a problem." Yeah, now it is *your* problem!
      • Re: (Score:3, Insightful)

        by Cylix ( 55374 )
        Surprisingly enough, there are fields that pay much better which require a broad range of expertise.

        However, no one will dare mention all of the real requirements. You see, the valid candidates will run screaming away because it looks to be too much, but what you end up with is a person who scoffs at all the extra that wasn't mentioned when he was hired.

        Thus, eventually the cycle continues until you no longer need the jack of all trades and have many very specialized people who cannot get anything completed
      • I'm with you man. I would prefer to get 10 years of experience rather than 2 years of experience 5 times (aka working in a job with one hat where you do the same thing over and over again).

        Of course you're always going to specialize...and hoping learning new things in that field everyday. The second that I have been practicing at a high level for a couple of months in a field is the second that I start training my replacement while I look for something new to sink my teeth into. That way I mostly mast
      • You're not alone.

        I'm an IT guy now who also wears a dozen hats. I'm also a Business Management student, and a frequent topic of discussion is about generational differences in the American workforce. It's been noted that past generations would trade all kinds of job satisfaction in return for job security. More recent generations are not so willing. Businesses have also changed. Companies expect greater turnover, are more flexible than they used to be, and operate "leaner" than they used to.

        There's alw
    • by TiggertheMad ( 556308 ) on Wednesday March 05, 2008 @01:26AM (#22646420) Homepage Journal
      Could the emergence interdisciplinary experts lead to another 'renaissance' of sorts?

      Oh, I don't know. If only we had a art history & statistics dual major to figure it out...
    • by Rakishi ( 759894 )
      There are a fair number of scientists who know multiple subjects, most of them simply don't become well known. They may make some great new application of physics to biology but they probably won't make breathtaking discoveries in either. Likewise since it's easier to just study one subject and people generally seem to only be interested in one area you also get fewer people who can and do work across multiple fields.

      Actually any good scientists nowadays probably knows more from across different fields than
    • Re: (Score:3, Interesting)

      Or could the existence of things called "printed books" lead to the spread of knowledge among others who could use it, rather than having to build up their theoretical knowledge from personal experience and a few precious manuscripts? And make it more broadly available so that people with less than mutant brilliance can contribute andn publish their contributions for others?

      I don't think you need to read in any great cultural change to a cross-disciplinary approach here: the problem is one well-suited to th
  • Umm.... (Score:5, Informative)

    by palegray.net ( 1195047 ) <philip.paradis@p ... net minus author> on Tuesday March 04, 2008 @11:42PM (#22645886) Homepage Journal
    He might be a psychologist, but his venture firm is named Mathematical Captital [mathematicalcapital.com], after all. His partners appear to have advanced degrees involving mathematics.
    • They are also entered in the competition separately from the guy in the garage and are in the top 15 - 20 places by the look of it.
    • I read the Wired article originally in the magazine and according to it, his high school senior daughter is doing all his math work for him. I'd be really impressed if just the dad and the daughter wrote every algorithm themselves.
  • Psychologist? (Score:5, Insightful)

    by Otter ( 3800 ) on Tuesday March 04, 2008 @11:43PM (#22645890) Journal
    I don't understand why Wired insists on playing along with Potter's pretense of being an "unemployed psychologist". He's a PhD candidate in machine learning, has a masters in operations research, is ex-IBM and Pricewaterhouse, runs a VC firm -- he has plenty of quantitative and computational training and experience, probably more than most of the contestants.
  • by GregPK ( 991973 ) on Tuesday March 04, 2008 @11:47PM (#22645912)
    My extensive retail experience says people like to shop by the following methods. Ratings, Genre, Alphabet.

    So, if I was to setup a movie viewing for them. I'd setup something along the lines of a Genre, rating(R,PG-13,G), Alphabet.

    It's kind of a takeoff on my video game organization method that increases sales of video games by 30 percent. I called it ABSRG short for Alphabetize By Section(4 foot section), Rating(M on top T in the middle and E towards the bottom.), Genre(Sports, driving, shoot em up). Please note, this cannot be patented, I already let it go out for more than a year(Started in 1998)and I have the pictures and time notes to prove it.
    • Organising the physical games in that manner cannot be patented - but doing it over the Internet is a totally different thing. Or at least that's how it seems to be.
  • Free Idea (Score:5, Interesting)

    by Speare ( 84249 ) on Wednesday March 05, 2008 @12:25AM (#22646120) Homepage Journal

    Okay, I'm not trying for this prize, but there's one thing about Netflix "recommendations" that bugs me so I'm throwing out this complete freebie of an idea. If it helps someone get a 0.001% improvement to add this ONE little additional check, great.

    I am learning Japanese. I have been watching several hundred Japanese-language movies for the past couple years. I don't watch movies in Greek, Spanish, Turkish, Farsi, Italian, Russian, German, or Hebrew. I did watch Amelie four years ago but that doesn't mean I love French movies. Most of my recommendations are for foreign films, but only a small fraction of those recommendations are for Japanese movies.

    Apparently, Netflix doesn't have a column in their database saying WHAT language a movie uses principally, it just has a flag saying it is not English. It's the only explanation I can see for not checking for such a strong correlation. I admit, I might not be sharing the experience of the most common movie-renting drone in the bunch, but I doubt I'm the only person who has such a lopsided taste in movies. If the language (or alternate soundtrack languages) ARE known in the database, please see if the renter has a bias for movies in a particular language.

    • Apparently, Netflix doesn't have a column in their database saying WHAT language a movie uses principally, it just has a flag saying it is not English.

      It doesn't store any data about the language, actually. (It's at least not something that is available for the contestants.) All relations between movies (same language, similar length, same genre, same actors, similar number of characters and what not) are supposed to shine throught in users' ratings. That means that with enough ratings in the database, yo

    • by tgv ( 254536 )
      Try movielens (http://www.movielens.org/): it does offer a search with specific languages.

      You might also try to copy my recommendations, since it recommends quite a few Japanese movies based on that...
    • by shmert ( 258705 )
      This whole contest seems flawed. There's obviously some limit to how accurate an algorithm can be, you'll never completely predict how some person will rate a movie. You might as well try to predict what someone is going to type in a slashdot post. Sure, "First Post" is easy, and some people are more predictable than others. I'm sure there are patterns in the movie ratings of individuals, but they're not going by any strict rule of human nature.

    • They make tentacle porn in Greek, Spanish, Turkish, Farsi, Italian, Russian, German, amd Hebrew?

      You learn something every day.

  • Does anyone know how big the dataset download is and what the format is? The website wants a registration before it lets you download the dataset.
    • by Paeva ( 1176857 ) on Wednesday March 05, 2008 @12:47AM (#22646230) Homepage
      The dataset is about 660MB to download. It unpacks to 2GB of about 18,000 text files.
      • Thanks, I just want to have a rough idea of the mathematical complexity of the problem :)

        As I understand from the rules, each customer rates a bunch of movies. How many customers are there? How many movies? How many ratings does each customer do (on average, perhaps)?

        • by Paeva ( 1176857 ) on Wednesday March 05, 2008 @01:10AM (#22646354) Homepage
          There are 480,189 customers that rated 17,770 movies. The total number of ratings that you're given is 100,480,507. Each user/movie/rating is accompanied by the date of the rating, as well. You then have to submit predictions for the ratings of 2,817,131 additional user/movie combos (they tell you the user, the movie, and the date, and you need to predict the rating). You submit these predictions to Netflix, and they tell you the root-mean-square error between your predictions and the actual ratings that those users gave those movies.
          • Many thanks. Just one more question: for the test set, are the users and/or movies all existing users and/or movies (from the training set), or can they be essentially unrelated (ie a movie which was not rated by anybody before, or a completely new user)?
            • Re: (Score:2, Informative)

              by Paeva ( 1176857 )
              Each of the movies and each of the users represented in the test set have some corresponding known ratings. I think the minimum is around 10 known ratings for users and maybe 3 or 4 for movies. And there are examples on the opposite end of the scale... one user has rated nearly every movie in the training set, and most of those ratings were 1 star. If you have any more questions, feel free to check out my blog - my Slashdot profile links to it, and you can find my email there. I'm Dan Tillberg, currentl
  • by Gorimek ( 61128 ) on Wednesday March 05, 2008 @12:40AM (#22646188) Homepage
    Being beaten up is normal for any nerd, but by a Psychologist - that's gotta hurt...
  • by zappepcs ( 820751 ) on Wednesday March 05, 2008 @01:00AM (#22646302) Journal
    Yes, the story is old now (by Internet standards) and no, he's not actually winning. What he did do was make a great leap in the success of his process by using a better group of knowledge for a base to work with. This is neither new or amazing in anyway. The only reason it makes news is that it's so much common sense that the story is told as if he has had some huge breakthrough.

    Even if he only gets to 9.25% I will bet he gets offers to work with AI researchers around the globe. That is, after all, what their stated goal is - more or less. Every programmer knows about the GUI wars, and has read stories about how programmers have trouble writing code or designing web sites that are intuitive for users. If you want to see you code break, put a user on the keyboard and wait a few minutes.

    Just about everything that I do with computers shows me something that could be more impressive or intuitive. Can you say 'click START to shutdown' ? Applying psychology and math to a computer problem is a problem that programmers are faced with all the time, and the industry as a whole fails on this repeatedly. A matter of personal interest, hobby robotics, holds a particular problem that seems simple but is not and demonstrates the scope of the problem with this story. Try to build a small robot that can wander around your house and never get stuck behind the couch, or anywhere else. Even cockroaches can accomplish this, but sophisticated robotics cannot.

    We've all seen people come from nowhere, solve a problem because they looked at it a different way than everyone else based on their experiences. I think that it is about time that we started doing more of this. The biggest problem that I can see thus far is that people don't act like computers, they seldom repeat anything with precision. Can you say manufacturing robot? Everyone of us has personal tastes, and it's usually only when Hollywood tells us what movies are good that we all fall in line. Sure, some 'blockbusters' fail, but they make money because of the hype. When you remove the hype, it falls apart. Picking out what other people like or might like based on a very small data set is a difficult task. Not everyone likes kids or movies for kids. Not everyone likes hollywood-ized cookie cutter movies. The task is daunting at best.

    Apply that thinking to other things, and you can see why some websites work and others do not. Why some software works and why others fail. Should F1 be the help key or F3? Why not CTRL-H? Maybe your preferences for such things differ from mine. What I'm getting at is that predicting what a human will do is not simple. Categorizing movies by story, style, genre etc. is like applying a tag cloud to it and matching the tag hits of one group to your personal tag choices. It kind of works, kind of does not. Either way, it needs to be applied more often. Just today I received a thank you note from the local Honda dealer where I got my seat belt replaced under warranty. I bought the car 15 years ago from the dealer my mother likes, and is two states away from me now. The dealer that send the card is local to me (2 states from my mom) but they sent the card to her, at MY address. Tell me how a human would have done that?

    The basic problem is that we humans accrue various bits of information and make decisions based on that. Our thinking process halts when something 'just doesn't make sense' to what we are doing. Computers don't do that... yet. Perhaps this guy is on to something, but then maybe not. A human would not only ask what other people liked this movie, but also "you really liked that piece of crap?"

    To put the I in AI is going to take a lot of rethinking. Simply acting like a perfect human won't do it. Oh, you liked that movie? yeah, me too, I love the city where it was filmed. -- get a program to do that? That oddball out-of-left-field thinking is what will make the software very good at predicting what you will or will not like, maybe.

    Have you ever tried to figure out what kind of music someone would like from your collection? Yes, it's not easy unless their tastes are so much like you that you can't miss. That is the scope of the netflix problem.

    Now, to add the punchline. Get your trigger finger on the off-topic button, but the MPAA has been telling us what we want to watch for so long that it has skewed the data beyond repair. Well, perhaps. The Independent Film Channel has helped to re-introduce non-hollywood films. Movie rental stores have helped. As long as film distribution remains largely in the hands of a few people, the problem will remain. The data, the tag clouds remain unintelligent when most of the populace is hand fed a shortlist of films from a precious few people in Hollywood.

    I'm willing to bet that this guy's progress is stilted because of the skewing of the data because of the MPAA effect. If it has not been remade by Hollywood, North Americans hardly ever see the film, and this slants the data. Sure, knowing the slant might help, but I think not. The same skewing has taught North Americans that bottled water is better than tap water... WTF is that? Yes, humans make decisions based on information that is often not good information. Programs rarely ever do. They normally fail when not enough information is available. This is an attempt to answer as best as they can without enough information.

    If you've read this far, you probably get it now. This algorithm is the reverse of the Hollywood advertising machine. One tries to get everyone to like the same thing, the other tries to figure out what everybody likes. When both are operating in the same space, you are sure to get a divide by zero error every now and then.

    I think he has done well, and hope that more people build on his success.
  • And? (Score:4, Interesting)

    by Secret Rabbit ( 914973 ) on Wednesday March 05, 2008 @01:19AM (#22646382) Journal
    There a joke that I heard (that's actually pretty much true):

    A Physicist goes to a Mathematician for advise on solving a Differential Equation. The Physicist explains this and writes the equation on a Blackboard. The Mathematician stares at the equation for more than half an hour. Finally, he says, "Yes, it has a solution."

    Basically, the Maths (even applied) are about details and considering them *very* carefully. With this in mind, is it any surprise that they are somewhat "slow"? Especially when they are starting from scratch within the problem domain?
  • by Shazow ( 263582 ) <andrey...petrov@@@shazow...net> on Wednesday March 05, 2008 @01:58AM (#22646570) Homepage
    The team at the University of Toronto, who are using a neural networks approach, are led by Geoffrey Hinton [wikipedia.org] who has a bachelors degree in experimental psychology.
  • by robhiller ( 757839 ) on Wednesday March 05, 2008 @05:19AM (#22647252)
    Am I the only one that finds the phrase 'An almost-anonymous British psychologist named Gavin Potter' faintly ridiculous?
  • According to the Fine Article, This "just a guy" not only is a psychology major, he has an OR (operations research) masters, which is basically applied math : optimisation, statistics, etc. This is just the kind of winning combination for this type of problems.
  • I lost a job because of a bad psychologist report, some lies from workmates who hate me, a 3 page multiple choice test, and 10 minutes talking about my father, and he thinks hes got the right to ruin my career.

    Psychologist: Oh, so the problem with your video delivery service is that it has bipolar disorder, gender-orientation issues, and a reverse oedipal complex with a double backflip and extra chocolate sprinkles. Throw it on the scrap-heap and write a new system from scratch.

Our business in life is not to succeed but to continue to fail in high spirits. -- Robert Louis Stevenson