Slashdot is powered by your submissions, so send in your scoop


Forgot your password?
Movies Media Software

Software Predicts Movie Success 192

scheming daemons writes "TechNewsWorld has an article about software that predicts whether a movie will be successful or not by factoring in its rating by censors (e.g. G, PG, R), strength of the cast, genre, competition from other films at the time of release, special effects, whether it is a sequel, and the number of theaters in which it will show."
This discussion has been archived. No new comments can be posted.

Software Predicts Movie Success

Comments Filter:
  • by Spazntwich ( 208070 ) on Saturday December 17, 2005 @11:39AM (#14279659)
    A good script?
  • by grub ( 11606 ) <> on Saturday December 17, 2005 @11:41AM (#14279662) Homepage Journal

    Score = (numCarChases + numExplosions + numTits) / (budget/1000000)

    • by Anonymous Coward
      Wait, so bigger budgets score AGAINST a movie?

      And, this formula WONDERFULLY explains the COLOSSAL sucess of 'Showgirls'...
    • overtraining. (Score:5, Insightful)

      by goombah99 ( 560566 ) on Saturday December 17, 2005 @11:55AM (#14279731)
      Yet another example of some machine learning bozo overtraining on a dataset to come up with a perfect predictro of historical data with little value for generalization. No doubt they have some dull understanding of cross validation which they mistakenly believe assures they have not over trained. Heh. In the end just as good as your linear numTit predictor.

      And then when they are done they find that any future predictve power it has only is focused into a couple of clusters that any fool could have told you were sure bets. It has not value unless your goal is to recycle the same things over and over till there's just one tru formula that all money making movies must follow.

      I suspect movie making is probably a lot like the stockmarket. While there's general themes that always have positive returns, the can't be a formula for big success because if there were then once it was known it would not work anymore. Originality and a cyclic nature of traditional themes is the flow but not predictable.
      • Re:overtraining. (Score:4, Insightful)

        by geminidomino ( 614729 ) * on Saturday December 17, 2005 @11:58AM (#14279744) Journal
        It has not value unless your goal is to recycle the same things over and over till there's just one tru formula that all money making movies must follow.

        You think this isn't their goal?
      • Sure, you'll inevitably have a system that only predicts that "more of the same" is good. That only picks sure bets. But as we've seen often enough in Hollywod movies (as opposed to moviemaking in general) sure bets often aren't. And if a system can help in picking which Tom "The Thetans Took My Sanity And All I got Was This Lousy T-shirt" Cruise vehicle will actually break even then I guess it will have fulfilled its purpose.

      • How do you know this guy is a bozo?

        How do you know he overtrained his system?

        I have just enough experience with these subjects to conclude that the article hasn't given enough information to make a decision in either direction.

        I'll admit that this system doesn't have a whole lot of value when it comes to fostering creativity, and may even stifle it by placing another strike against small-budget films that could defy the odds. But in an industry that frequently makes $100M "oopsies", it may have some value.
        • "But in an industry that frequently makes $100M "oopsies", it may have some value."

          If a bunch of studio executives with a lot of hollywood experience and a lot of money to lose can't figure out that these movies will be "oopsies", why should a non-intelligent computer program that extrapolates results based on a few broad parameters do any better?
          • Well, you've got "herd mentality," nonsensical "common wisdom", over/under-reliance on certain factors, and a litany of other impediments to making proper decisions. Neural nets have a rather different set of impediments, and in an ideal world the two approaches can compensate for some of each others weaknesses.

            In the real world, this tool will be touted when it's saying what the execs want to hear, and dismissed as hogwash when it predicts failure. So I really don't see it making a big difference either
        • How do you know he overtrained his system?

          I have just enough experience with these subjects to conclude that the article hasn't given enough information to make a decision in either direction

          Apparently not. Read the article again and then re-read my post. First I do explain in part why I think it is hopeless: the cylclical nature of the favorite and the likilihood that good movies lie outside the main clusters.

          But read the article and you see he claims 75% accuracy on 7 catagories if he is allowed a bin p
      • Note the "formula" depends partly on "the number of theaters the film opens in". Will a studio pick this number at random? Or perhaps they open big with movies they expect to be big? It's like a horse-racing pick that tells you to bet on the favorite; i.e. the one that most people expect to win; not through analysis of the horse (movie) itself.
    • One small adjustment:

      Score = (numCarChases + numExplosions + numTits^2) / (budget/1000000)

      I think you underestimated the power of tits.
  • It seems their has been a recent spurt of "smart" systems like this...

    Maybe we're finally coming out of the "AI Winter" it seems like we've been in for a decade or so...

    • I expect it's less of an AI and more of a simple collection of linear statistical models (linear regressions and general linear models) using parameters gleaned from the performance of past films.

      Unless yours was a reference to the awful film A.I.
  • The code (Score:2, Funny)

    by Anonymous Coward
    int main() {
        if ( this_is_mainstream() ) {
            if ( good )
                return 1; /* error */
                printf("50 Million USD");
        } else
            printf("Sued out of existence before it's released");

        return 0;
  • King Kong (Score:2, Interesting)

    by Inaffect ( 862616 )
    "To predict whether 'King Kong' is going to be successful, I don't know how important that is. But to predict something that is a little bit more esoteric is a more difficult task."
    His software didn't tell him how important it was?
    King Kong is flopping like a pancake...
  • Program?? (Score:5, Insightful)

    by malraid ( 592373 ) on Saturday December 17, 2005 @11:44AM (#14279676)
    I can do this with Excel and some previous statistics! How breaktrough it this? Of course, if it's a program that analyzes the script, that would be another matter, but it's not.
    • Re:Program?? (Score:4, Informative)

      by erikus ( 891552 ) on Saturday December 17, 2005 @12:25PM (#14279847)
      actually, they did use excel. google cache []
    • Excel my as (Score:2, Insightful)

      by TubeSteak ( 669689 )
      I think this is something statistically minded /.'ers are aware of: there is a difference between
      1. Creating a formula based on your theories and finding that the data you run data through it is well explained by your (weighted) equation.
      2. Taking a bunch of numbers and having the computer find the best equation that explains the data.

      One of those two methods is bad math

      A computerized analysis of 834 films demonstrated a significant level of accuracy in gauging their financial success.
      diff article:
      The programme,

      • >>2. Taking a bunch of numbers and having the computer find the best equation that explains the data.
        >>I seriosuly doubt that he picked Method #2
        >> you'll discover they're using a nerual network

        Using a neural network, in fact, means that they let the computer find the best equation. It's just that with a neural network, you don't get to know what it is.
      • One of those two methods is bad math
        Which one? Why?
        Regression is an accepted method to generate a model from data. Of course any model has deficiencies, that where good logic comes into play, to identify those deficiencies, and correct them if possible. It may have taken the professor 7 years to define the right variables and collect the data, but once the data is available, the model can be constructed within a couple of days using Excel.
      • Regression is usually the first step to creating a model. It's where you analyze trends and discover variables.
    • You would gett more karma if you used Calc or gnumeric ;o)

  • by gasmonso ( 929871 ) on Saturday December 17, 2005 @11:47AM (#14279691) Homepage

    The big recording labels had developed software to determine the quality of song. Apparently, they could determine if a song would be a megahit or a flop. Judging from what I've heard on the radio, it doesn't seem to work. Hopefully the movie industry will have better success. []
    • by owlstead ( 636356 ) on Saturday December 17, 2005 @12:17PM (#14279820)
      No, hopefully, they won't have (better) success. More sucky movies can only be the result of this.
    • program DetermineHit
      implicit none
      logical :: isRIAA

      write(6,*) "Is this track published by a corporation which is a member of the RIAA?"
      read(5,*) isRIAA

      if (isRIAA) then
            write(6,*) "Track will flop"
            write(6,*) "Track will be a hit"
      end if

      end program DetermineHit

      !what's so hard about that?
    • by rolfwind ( 528248 ) on Saturday December 17, 2005 @12:39PM (#14279901)
      I suppose what these type of algorithms really say is how close a song (or movie) followed a successful formula - but it cannot predict a new genre of music (or movie) and will give you a false negative on it's success.

      In any given genre - there was one or a generation of breakthrough artists and then the imitators get quickly spawned off to leech off that success. These algorithms try to predict the success of the leeches.

      Just watch TV for confirmation - CSI becomes successful - there are X,000 CSI like shows on TV now. Medium becomes successful, how many medium-type show are on TV now? (I'm not saying these are the original trendsetters, but the original ones for this TV cycle).

      But if the creative arts are tested against these algorithms, diversity will die and so will the audience as everything will become the SOS (Same Old Shit, more than it is now).
    • Apparently, they could determine if a song would be a megahit or a flop. Judging from what I've heard on the radio, it doesn't seem to work.

      But you are listening to it on the radio, so the industry has already won.
    • Apparently, they could determine if a song would be a megahit or a flop. Judging from what I've heard on the radio, it doesn't seem to work.

      It will never work. This is because when several companies have software that will predict something collide, they compete and we end up with recycled drivel.

      This is similar to stock market analysis software. A software program that (hypothetically) successfully predicts which stocks will rise stops working as soon as a bunch of people use it.
  • But what about (Score:4, Insightful)

    by udderly ( 890305 ) on Saturday December 17, 2005 @11:48AM (#14279692)
    Napoleon Dynamite? I find it hard to believe that this script would have predicted the success of this film.

    Also, this actually kind of disgusts me since it seems IMHO that it relies on the same formulaic approach that's responsible for the poor offerings that Hollywood is currently producing.
    • When it comes to "Napoleon Dynamite", I'm still scratching my head trying to figure out why anyone liked it. I was amused at a couple of points, but mostly it was just dull and painful to watch. If I were building this software, and it kept telling me that this film would rake in the bucks, I'd probably end up deleting it and starting from scratch.

      I shouldn't rag on you for liking it, though. God knows I've loved lots of movies that everyone else hated. There's no accounting for taste, especially mine.
      • I wonder if the reason it did so well was because it won some kind of movie award on MTV .... concidentally didn't MTV produce the movie too?

        Mmmm.. MTV Sheeple.

        • Have you seen the movie? I was not aware it was produced by MTV until their logo popped up... I was disappointed, but oh well. The idea for the film certainly didn't come from MTV; the DVD includes a short black and white precursor to Napoleon Dynamite. For me, I think the quality that separates films I really like from films only mildly entertaining is something like a vibe of honesty or love.. Like, I feel that Napoleon was produced in order to make a funny movie, not in order to make money. I just w

  • Infallible? (Score:4, Funny)

    by rvandervort ( 721261 ) on Saturday December 17, 2005 @11:48AM (#14279694)
    rating by censors (e.g. G, PG, R), strength of the cast, genre, competition from other films at the time of release, special effects, whether it is a sequel, and the number of theaters in which it will show.

    Hmmm...I wonder what it had to say about Waterworld...
    • It doesn't need to predict success a 100% of the time. All it needs to do is predict it a majority of the time for the studios to keep making a shit-ton of money.
  • by russellh ( 547685 ) on Saturday December 17, 2005 @11:48AM (#14279696) Homepage
    Suddenly I'm thinking of the measure of the greatness of poetry scene from Dead Poets Society. Right on. Yeah, I know, it's not about greatness, it's about box office success. I bet they left Gigli out of their tests.
  • by Dr. Spork ( 142693 ) on Saturday December 17, 2005 @11:50AM (#14279704)
    If this thing does any good predicting at all, I'm sure it's based on the number of screens that the movie shows on. Once you have that number, I'm sure your pick will usually be pretty close. This is because the theater companies pay public opinion eggheads big bucks to figure out how many screens to reserve for movies... based on the movie's expected audience draw. These theater people do the actual analysis. To piggyback on their results and then pretend you were the insightful one seems really ... unimpressive.
    • except where success in the equation is the known variable (ie, they want it to be successful) and # of theatres (or any other factor) is the unknown. then they can simple adjust the other numbers until success is achieved.
    • Box Office Mojo has a forecast game [] and does this every week. The only info you get is number of theatres.

      I'm sure it's based on the number of screens that the movie shows on. Once you have that number, I'm sure your pick will usually be pretty close.
    • The article says as much:

      On the other hand, predicting the potential success of a film based on a set of factors is what movie studio executives are paid to do, Peterson acknowledged. It may be interesting to automate the process, he said, but the software would only support industry behavior that already exists. "Film executives look at things like star power, film release dates, target audiences and soundtracks," Peterson said. "This software is going to give you information that is probably already kn

  • by bcnstony ( 859124 ) on Saturday December 17, 2005 @11:53AM (#14279720)
    Many of the criteria used here are subjective, and based upon existing human estimation of the movie's success. For instance, when a movie opens in a large numbers of theatre's simultaneously, it usually means people have already predicted it will be successful. Also, movies are often chosen to 'Open' on a date that doesn't conflict with other movies, and is chosed to maximise revenue. It's a real stretch to call this software's process 'scientific'.
  • by Dachannien ( 617929 ) on Saturday December 17, 2005 @11:54AM (#14279725)
    Network President: Greetings, gentlemen. You already know my execubots: Executive Alpha, programmed to like things it has seen before.
    Executive Alpha: Hey hey hey.
    Network President: Executive Beta, programmed to roll dice to determine the fall schedule.
    Executive Beta: (rolls dice) More reality shows!
    Network President: And Executive Gamma, programmed to underestimate Middle America.
    Executive Gamma: It's funny, but is it going to get them off their tractors?
  • by Funakoshi ( 925826 ) on Saturday December 17, 2005 @11:54AM (#14279728)
    "...strength of the cast..."

    Will it be based on looks or on acting ability? There would be some serious issues if they used acting abilities. There are some horid actors/actresses that sell boatloads because they look great, and then there are some...well...less visually pleasing folks, that are fantastic actors/actresses.
    • No, it's how much they can lift.

      Seriously - most of these parameters aren't very quantitative. I want to see some code.
    • Will it be based on looks or on acting ability? There would be some serious issues if they used acting abilities.

      Well I've just been watching 'Star Trek: The Next Generation', from the beginning. And I can only say... theres a difference? Looks and acting ability can be *equally* bad and still make successful TV (yeah I know this is about movies but these days hey, I call the Brak show a 'movie', hows that?).

      There are some horid actors/actresses that sell boatloads because they look great, and then there ar
  • by Anonymous Coward on Saturday December 17, 2005 @11:55AM (#14279734)
    ...with formulaic movies is more formulas?
  • Statistically (Score:5, Interesting)

    by alphaseven ( 540122 ) on Saturday December 17, 2005 @12:07PM (#14279784)
    I have my doubts this will work. Like, statistically speaking, John Ratzenberger, the guy that played Cliff on Cheers is very bankable actor, he'd been in Empire Strikes Back and a couple Superman films, and all six Pixar films, so his films have grossed billions of dollars. I guess a computer might pick him to play the villian in the next Batman film, but in real life there isn't a magic formula.
    • This is the problem with formulas. They don't take into account anything except money..

      Pixar films are like going to the circus, you know you'll get a few laughs, see a few animals, have some pop corn and generally have an enjoyable 2 hours. It's more or less a risk free movie, children will all adore it and want to see it. Parents will get dragged along (my parents often goto see Pixar films and they're not into films at all) and end up enjoying the slap stick comedy just as much as the kids.

      Star wars is a
      • Re:Statistically (Score:2, Interesting)

        If you've got The Incredibles DVD, there's a bit in the directors commentary about the use of John Ratzenberger. ISTR Brad Bird saying something about not wanting to risk the movie without his presence in it, like a rabbit's foot.
  • by spirit_fingers ( 777604 ) on Saturday December 17, 2005 @12:07PM (#14279785)
    This is what happens when the bean counters try to quantify the creative process. You can add up all the ingredients for a hit movie and still have a major bomb on your hands.

    It's like saying you can dump fois gras, Chateau Latour, beluga caviar and a savoy truffle into a blender and end up with the world's most wonderful milkshake. In the end it's a recipe for mediocrity, at best. More often, all you get is expensive puke.

    If one could predict success by adding up the elements that go into movie making, then "Catwoman" should have been the megahit of 2004.

    • dump fois gras, Chateau Latour, beluga caviar and a savoy truffle into a blender

      This is just like sesame street. Which one of these doesn't belong? :)

      (Hint, Savoy Truffle isn't a fungus).
      • From Wikipedia:

        Harrison wrote the song as a tribute to his friend Eric Clapton's chocolate addiction, and indeed he derived the title and many of the lyrics from a box of Mackintosh Good News chocolates.

        So... it may not be a fungus, but you could drop chocolate truffles into a blender with the rest, too. :)

    • I doubt they'll be turning over the entire film-selection process to this software, or any of its descendants. For one thing, too many jobs are at stake. Rather, this may end up effectively automating the sorts of formulas the industry already uses to guess at the success of movies, which will save labor without significantly changing the results.

      One of the best things you can do when coming up with a system like this is to create some sort of baseline to compare it against. For example, if you want to k
  • Pure garbage (Score:3, Insightful)

    by Aaron32 ( 891463 ) on Saturday December 17, 2005 @12:17PM (#14279822)
    rating by censors (e.g. G, PG, R) strength of the cast genre competition from other films at the time of release special effects whether it is a sequel and the number of theaters in which it will show." It's ridiculous to expect software to predict entertainment. From the above, success can only be even remotely predicted by "the number of theaters in which it will show". And possibly the "strength of the cast". Mainly I think the trailers shoved down our throat with only the best parts of the movie could help success. I highly doubt this software would have predicted the success of The Blair Witch Project. Zero special effects, zero strength of the cast, zero budget.
    • The thing isn't trying to judge artistic quality or entertainment value, any more than it's trying to judge "social responsibility" or any other abstract concept. The only goal is to figure out how commercially successful the film will be.

      If the factors you listed as important were the only factors that really influenced the outcome, that would have manifested in the strengths of the neural net. It's very possible that the creator had a couple of other factors he was looking at, which didn't significantly
  • by Aaron32 ( 891463 ) on Saturday December 17, 2005 @12:22PM (#14279838)
    success = IMDB.com_USER_RATING
  • by sam_handelman ( 519767 ) <> on Saturday December 17, 2005 @12:23PM (#14279840) Homepage Journal
    With 9 revenue categories, correctly predicting the category 37% of the time (RTFA), is, ehem, unimpressive - a dartboard would guess correctly 11% of the time.

      So we have a predictor that makes 0.63/0.88 ~= 70% as many mistakes as a dartboard. If you give it one category of "wiggle", it makes 0.25/0.66 ~= 40% as many mistakes as a dartboard.

      People are making a lot of hay out of this. It tells you that small movies (opening on fewer screens) are very seldom blockbusters, and that heavily promoted movies almost always make at least ten million or so. How is this unexpected? I bet I could get similar predictive power using a SINGLE variable - the promotion budget for each of the films. If it could tell us something actually interesting (or useful to hollywood types) - like "why are some big budget movies successful while others are not?" - that might be worth something.

      Also, the journalist is a nitwit - "North American ticket sales currently total $7.6 million."

  • Hollywood uses similar metrics for most of their features.

    This explains more than anything else why the quality of the majority of movies dropped so fast in the last few years.

    None of those parameters can measure (digitally) the quality of the story, quality of acting (note: not popularity of the cast, Pam Anderson is also popular) and quality of the movie anyway.

    Hearing from buddies or critic reviews, that a movie is poorly done mix up of popular actors, effects and soft porn with dumb as stics scenario st
  • Awesome-O (Score:5, Funny)

    by millennial ( 830897 ) on Saturday December 17, 2005 @12:32PM (#14279871) Journal
    This is unbelievable! Awesome-o has thought up 1193 different film ideas. 906 of which star Adam Sandler!
  • by MS_leases_my_soul ( 562160 ) on Saturday December 17, 2005 @12:34PM (#14279879)
    First of all, if I was only 37% successful at my tasks at work, I would be out the door in a heartbeat. One category off could mean the difference between success or failure.

    Where this gets stupid are the advertising, word of mouth, and "fanatic" factors.

    First, if a studio thinks a film is going to tank, they won't advertise it and won't push it to as many screens. As a result, less people even know the film exists and even if they do, it is harder to find. I can think of several movies that were awesome films that were just not advertised. I never saw a commercial for Usual Suspects, but saw it after a friend said it was the best movie they had ever seen. If the studio predicts failure, it could be a self-fulfilling prophesy, but I think the age of quick DVD release and peer recommendations is changing this.

    That brings me to the second factor - word of mouth. How do you put word of mouth into a formula? Maybe I am in a very small minority, but my interest in a movie goes up significantly if a trusted friend (key point, others I do the exact opposite of what they say) says it is am AWESOME movie. They rank many movies as good, but very few as awesome. So what is the Awesome determinator? A movie can creep out of nowhere and just keep growing on the word of mouth factor. I admit that this is not a common event, but one that would seem nearly impossible to predict.

    Finally, the fanatic factor. Remember where fan comes from. There are certain writers, directors, actors, soundtrack performers, etc. that carry a certain draw all on their own. Josh Weadon could write a movie about a girl who has poo flinging superpowers and tens of thousands of fans would go see it based on his name, but almost all would be inside a tight demographic. 37% sounds about right in this area.

    As a final addition, there is the stupidity of Hollywood factor. They make movies based on what movie-goers like. There are less movie-goers each year because there is less for movie-goers to like. Why pay $25 for tickets, coke, and popcorn to take the wife to see a movie when I can go the big screen TV, NetFlix, and Newman's Own Microwave Popcorn route? My wife would probably add the "you can't pause the theater movie to go pee" factor, too.

    Hollywood responds with stupid formulas like this that lets them focus on certain formula films fed to certain demographics and expect a simple equation where you fill in 40 variables and get instant profit. Political and religious discussions aside, the Passion totally breaks the mold. I went with 10 people to see that movie in the opening week and 6 of those people had not been to a theater in years.

    The box is getting smaller each year and each year Hollywood continues to segment the box into what it thinks is the most profitable section, throw their efforts there, and alienate another years worth of eyeballs out of the box.

    My hope is for alternative delivery and an uprooting of the current studio/distribution model. When the fanatics have a mechanism for funding a film or tv series that goes to internet and/or dvd delivery, the whole world changes. There are multiple ways to do this, too. Fans could pre-pay for a season of tv in order to get the dvds as they are made instead of in a boxed set (with no rental/netflix option until the boxed set was out). A film company could put up a bond that they would sell to the fans for a share of the profits.

    If you really think JMS is so awesome, how many $50 bonds would you buy? If he sold 100,000 bonds with a 20% of profit share, made the movie for the $5 million, and netted only $30 million on theater, pay-per-view, and dvd, you would still get $60 back for each $50 investment.
  • Ticket Sales (Score:2, Insightful)

    North American ticket sales currently total $7.6 million.
    That's got to be a typo, right? Or should I, for one, wave goodbye to our old MPAA overlords?
    • Obviously, since there have been several 100 million + movies this year. Billion would be approximately right (though still a little low, they topped 8 billion a couple of years ago).
  • by Stan Vassilev ( 939229 ) on Saturday December 17, 2005 @12:36PM (#14279890)
    1. make a db of meta info for already released movies

    2. make a software that conforms to the already existing stats and "guesses" the income. If it doesn't guess it, tweak until it "guesses" it.

    3. pitch it to Holywood execs by demonstrating it "works" by entering the same movie info you have already tweaked it for

    4. profit

    Of course the fact that it has (well, relatively poor IMO - 37% success? 75% "sort of success"?) success with the db of 800 movies is a result of it been tuned to work for those stats, and there's totally no guarantee it'll work for future releases.

    Especially that it can't and won't factor in the most important factor: does the movie suck after all or not.
  • by killmenow ( 184444 ) on Saturday December 17, 2005 @12:37PM (#14279895)
    ...factoring in its rating by censors (e.g. G, PG, R), strength of the cast, genre, competition from other films at the time of release, special effects, whether it is a sequel, and the number of theaters in which it will show."
    Of cours PLOT is noticeably absent.
  • by nberardi ( 199555 ) * on Saturday December 17, 2005 @12:47PM (#14279936) Homepage
    This isn't perfect because how would Passion of the Christ or Mystic River fit into this algorythm. There were no special effects, both were rated R, and one was in a language that hasn't been spoken for 2000 years. This is the problem with Hollywood today, they think there is a formula to good movies, good movies are good because they have a good plot, not high payed actors or special effects out the waazoo.
    • Ah, but you're missing the point: this wasn't a formula to see how good a movie will be, but how much money it will make. Two completely seperate issues.

      IMHO, it's very possible to determine the latter with this degree of success just by figuring out how many individuals are going to see the movie once. It's those people who go seven times that give it the error margin, and how do you quantify the quality of the movie?

    • It's not "all about the plot", there are only a finite amount of *interesting* plots and conflicts in movies. If you watch movies you know that the more you've watch the more predictable movies because there are only so many interesting plots that people will go to pay and see.

      Some movies are about the plots, others are the furthest thing from it. Look at thenew star wars episodes 1,2 and 3. All those movies I thought sucked compared to the originals (except maybe starwars "episode 4", they still dont ho
  • I am sure this is already in use by companies. They just need some finetuning and then we will be presented with the ultimate move.

    It will probably made by all studios combined as the outcome can only be one true movie. After that no more movies will be made.
  • by dankelley ( 573611 ) on Saturday December 17, 2005 @12:57PM (#14279982)
    The citation for the research paper is Ramesh Sharda and Dursun Delen, Predicting box-office success of motion pictures with neural networks, Expert Systems with Applications, Volume 30, Issue 2, February 2006, Pages 243-254. ( 3-4GV2PCH-1/2/35524bc2ff6fd852c98d8c9f3c3dc8c9 []). This is not a free journal, but if you're at a university it is quite likely that you have a library subscription. The paper is an interesting read, whether you're keen on film or on neural nets.

    The main result is that the method (neural net) works a little better than other methods on the same data (Table 4 of paper). It scores 75% in a test; conventional regression scores 71%. As they say in the statistical literature, "big woop"; the fancy new thing is marginally better than the simple old thing.

    As for the practical side of things, the main predictive variable is the number of screens on which the film was initially shown. The next-highest predictive variables are a variable representing the use of technical effects and a variable represengint the actors' reputation. Well, none of these indicates that this tool (or others discussed in the paper) is of any real use to the industry. The suggested use of the tool is to predict movie success. But the main predictive variables all represent things the industry already knew, when the film was being made and promoted. It's like asking a patient if they have a cold, and then charging them to tell them they have a cold.

  • Does it consider the Chewbacca Factor when rating Starwars sequels?
  • Dupe. (Score:3, Funny)

    by crhylove ( 205956 ) <> on Saturday December 17, 2005 @01:26PM (#14280086) Homepage Journal
    It's called the Awesome-O 4000:

    Um, Ok, how bout this, Adam Sandler, is like in love with some girl, but then it turns out, that the girl is actually a golden retriever, or something.
  • Pointless (Score:3, Insightful)

    by Doomstalk ( 629173 ) on Saturday December 17, 2005 @01:34PM (#14280120)
    Most of the factors it uses depend on a human already deciding that a movie's going to be a success. You don't get a star studded cast unless you think it's going to be a hit. You don't spend lavishly on special effects unless you think it's going to be a hit. And distribution size is determined by its commercial potential. When that's already decided, there's not much point to having a computer algorithm say the same thing.
  • by HuguesT ( 84078 ) on Saturday December 17, 2005 @01:49PM (#14280172)
    If this were 1990, the title would read "neural network predicts movie success" and the discussion would be about the impending success of strong AI.

    Reading TFA, it's impossible to know whether this study has any value without seing a proper article, as submited to a reputable stats journal.

    First of all this sounds like simple statistical classification with pretty obvious variables. However making classification work is not always trivial.

    Methodology is the key here. The sample of 800 movies is rather small, and the details on the chosen explanatory variables is sketchy. With enough variables, even meaningless ones, one can explain anything on a training sample. However with proper classification techniques, using for example jacknife/resubstitution/cross-validation [] one can find out if the classification model has any actual predictive values.

    As someone said "anybody can predict the past", and someone else "prediction is rather difficult, especially about the future".
  • by factoring in its rating by censors (e.g. G, PG, R)

    I do not think that word means what you think it means.

    Censoring a movie would be an accurate description if the MPAA actually edited the movie. They rate the movie which allows consumers to make an educated decision about seeing the movie.

    • censors (e.g. G, PG, R)

      I do not think that word means what you think it means.

      Main Entry: censor []
      Pronunciation: 'sen(t)-s&r
      Function: noun
      Etymology: Latin, from censEre to give as one's opinion, assess; perhaps akin to Sanskrit samsati he praises
      1 : one of two magistrates of early Rome acting as census takers, assessors, and inspectors of morals and conduct
      2 : one who supervises conduct and morals: as a : an official who examines materials (as publications or films) for objectionable matter


  • What would be particularly interesting is to examine the movies it failed on and attempt to understand why.
  • that this won't be very marketable. unfortunately, my software success detector says the same thing about itself, so i haven't bothered posting and ad for it on Slashdot
  • Is 2005 the year of the remake, or what?

    What movies were not remakes were almost all sequals, TV show adaptations, comic/children's book adaptaions, or biographies. What ever happend to an original idea? Can't you get that from software?

    "King Kong"
    "Willy Wonka"
    "Yours, Mine, and Ours"
    "The Bad News Bears"
    "War of the Worlds"
    "The Fog"
    "Oliver Twist"
    "The Longest Yard"
    "Damn Yankees"
    "Fun With Dick and Jane"
    revenge of the nerds

    Remakes in the works:
    "Doberman Gang"
    "The Birds"
  • From the end of the article, the author notes that the software is less capable of predicting the success of "off-beat" films like the Blair Witch Project.

    Suddenly I'm reminded of Asimov's fictional science of Psychohistory, which, in later books set in that universe written by Brin, Bear and Benford, which alluded to the fact that psychohistory was accurate only because humanity, under control for years by robots bent on making humanity happy, had managed to mane humanity incredibly predictable.

    Most movies
  • What the hell is the point of this? Why would someone spend time developing an algorithm that uses budget as one of the variables? Budget is something that would be based on an algorithm like this. So, this is basically saying: some group of people already decided that this movie is a good investment based on a number of factors; based on that,our formula thinks this movie will be successful, and it performs at a whopping 26% higher than chance.

    Well pop the champagne.

  • I can predict the success of a movie, also... ready?

    Where R = Ratings,


    There you go.
    Thanks, I'll be in all night.
  • I thought that such software already existed, and was called P2P. Really, it's simple: create a 700MB file containing some video footage (doesn't have to have anything to do with your movie) and share it on Fasttrack / Gnutella / whatever. The number of downloads = the amount of interest in the movie, which correlates directly on how many people will go see it on the theater.

    To keep from pissing people off too badly - remember, these are the people who are interested in the movie, and therefore most likel

  • Hell, you could have a machine pick an excellent plot (say from a book that sold excellently), choose a bunch of top-notch actors, and still have a bomb. How many book-adapted scripts sucked incredibly on the big screen?

    There is no magic bullet, if you make a stew from the best ingredients of 5 different other foods you can still end with something that tastes overall like strawberry-flavored-fish-in-marinara-sauce.

"I will make no bargains with terrorist hardware." -- Peter da Silva