What do you get when you mix information science with Hollywood’s film industry? Computer-based predictions of the next blockbuster hit.
Professor Ramesh Sharda, an information systems specialist at Oklahoma State University, has developed a computer program to help Hollywood predict the potential success — or failure — of a film.
Seven years in the making, Sharda has used his model to analyze more than 800 films on a set of factors decided long before the director ever yells “lights, camera, action.” The professor is publishing a paper in “Expert Systems With Applications” early next year.
Seven Critical Criteria
Sharda selected seven criteria on which to predict a movie’s potential viability in the marketplace. Those include 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.
Sharda’s model then computes the results and ranks the film in one of nine categories. “Blockbuster” status is given to movies that are expected to generate more than US$200 million in the box office, while “flops” are expected to generate less than $1 million.
Sharda’s study of the 800 analyzed films demonstrates a significant level of accuracy. The software predicted the right category for the film 37 percent of the time. Seventy-five percent of the time, the film ranked within one category of its actual performance.
Math Meets Movies
North American ticket sales currently total $7.6 million. That figure is down 7 percent from the year-ago period, but does not include revenues from “Harry Potter and the Goblet of Fire,” “The Chronicles of Narnia: The Lion, the Witch and the Wardrobe,” and “King Kong.” Could this technology be valuable to a film industry in a slump?
Yankee analyst Boyd Peterson told TechNewsWorld that Sharda’s is an interesting approach — akin to Wall Street’s dependence on mathematicians and physicists to crunch numbers that predict stock prices.
“The fact of the matter is that you can apply some discipline that gives you a range of success, but given the number of factors that ultimately contribute to success or failure of a movie, at best this model is only going to give you an idea,” Peterson said.
Off the Beaten Path
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 known.”
Peterson said the real testament of Sharda’s software would be if it had the ability to predict the success of a film that came out of left field and became a smash hit.
“Would his model have predicted that ‘The Blair Witch Project’ was going to be successful because the producers tried something different in terms of its marketing and distribution?” Peterson asks. “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.”