Unlike much of the public I really do listen to what critics say before I go to see a movie. I especially like Kenneth Turan and Joe Morgenstern who lend their critiques to NPR every week. Some of their best reviewed films happen to be ones you’ve never heard of, but will be sorry if you miss. It comes as no surprise that many of these movies don’t make a lot at the box office. As the number of crappy films that do make it to the screen increase every year, resulting in fewer people going out to see movies, studio executives need some sort of crystal ball or…formula to know which films they should greenlight for maximum profitability. Enter Professor Ramesh Sharda of Oklahoma State University. MSNBC reports:
A scientist in the United States says he has come up with a computer program that helps predict whether a film will be a hit or a miss at the box office long before it is even made.“Our goal is to try to find oil, in a way,” Professor Ramesh Sharda of the Oklahoma State University said Wednesday.
“We are trying to forecast the success of a movie based on things that are decided before a movie has been made,” he told Reuters by telephone.
<
p>Yes. That’s exactly what Hollywood needs. More formulaic movies. It’s even more discouraging when you see the variables that Sharda finds will maximize studio profits. Some of them are things that cause me to shy away from a movie:
Sharda applied seven criteria to each movie: its rating by censors, competition from other films at the time of release, strength of the cast, genre, special effects, whether it is a sequel and the number of theaters it opens in.Using a neural network to process the results, the films are placed in one of nine categories, ranging from “flop,” meaning less than $1 million at the box office, to “blockbuster,” meaning more than $200 million.
<
p>I wonder what would happen if you started entering Bollywood films into the system. I predict the system would crash. 
The system cannot take into account the intricacies of the plot, but Sharda says it can nonetheless get the revenue category spot-on 37 per cent of the time, and correct to within one category either side 75 per cent of the time. This is enough to make the system a “powerful decision aid”, Sharda says. [Link]
aww…first time i ever send a tip in (3 days ago) and i don’t even get a mention. bummer.
this brother might be a candidate for the IgNobels…
Sorry MJ, I don’t remember seeing the tip. I’ve been sitting on this story for a few days and finally got to it. Keep sending tips though.
On the bright side, the analysis may result in some the crappiest movies from ever being made 🙂
For any machine learning geeks out there:
I guess this is what they mean when they talk about feature selection!
Some scientists did this with music hits (mathematical formulas that were computer generated) and predicted that Norah Jones would be extremely popular. I heard of this on science Friday (National Public Radio) and on the National Geographic channel (on the t.v. show that follows new breathroughs in science and technology). I don’t think that this means that more crappy movies will be made but that perhaps there are certain qualities that make some movies universally popular (for the most part). This is why it doesn’t matter that Napoleon Dynamite and Bend it Like Beckham were made on a shoe string budget. There were some certain qualities that made them popular. Norah Jones is still a kickass singer/song writer even if her formula proves correct. Jhumpa Lahiri still is a talented and skilled writer whether or not her work is too adequate or formulaic. Crappy movies are going to be made with or without a formula. Hopefully the formula will give them a cohesiveness they lack?
Now, if only they could teach the computer to make the movie…
In fact, why not have computers replace not only the filmmakers themselves, but the audience as well? I know I’d be much happier.
I wonder what the computer said about Fahrenheit 911, March of the Penguins and Passion of the Christ, the 3 unpredicted hits that are making moguls cry out for mommy in their sleep these days?
Bakwaas. This is not gonna work in Bollywood at all. Case in point: Stupid movies that became superhits
I heard this guy on an interview for a show on npr called The World. They asked him about whether this might work in Bollywood… and his response was along the lines of ‘kinda, sorta, probably not… would first have to tweak it to account for songs’
Personally, Dr. Sharda is a genius. I know him personally and don’t always believe what you hear on the news or internet. He specfically states that this program is not intended to be accurate 100 percent of the time. It is only a secondary tool to help companies in their decision whether or not to make a movie. A good movie will be made even if the program says that it will be a flop but when it comes to the movies that producers aren’t sure of, they might turn to his program. His program WILL work in Bollywood. He specifically stated that it will be much harder for the program to incorporate the songs and other characteristics of movies in Bollywood because the movies are popular for different reasons, he just has to tweak the inputs for the program. It’s just research people so all you critics take a chill pill.