Mathematical model predicts Hollywood blockbusters
January 21, 2013
With Hollywood movie studios increasingly gambling astronomical sums of money on the next big thing, they might want to pay attention to the work being done by Akira Ishii at Tottori University. His research group claims to have developed a mathematical equation that combines advertising, word-of-mouth, and social networks to predict if a movie will be successful.
The model, which used the daily advertising budgets of 25 movies screened in Japanese theaters, calculated the likelihood of a person going to see a movie 60 days prior to the opening date through to 100 days after. They also took into account direct and indirect forms of communication, comparing their results to the daily number of tweets and blog posts for each of the movies. The resulting graphs outlined a person's intent to see movies such as Transformers, which lined up fairly accurately with actual box office revenues.
"Currently the calculations are such that they can't really be used other than by the students working in our lab," explains professor Ishii. "In the future we'd like to incorporate the equations into software that is easy to use by marketers or non-technical people that aren't so familiar with mathematics. Our dream is that our software could be used by advertisers or for conferences in a broad range of industries."
The group, which is listed as a business partner of a company called Hit Content Laboratory, says the model could be applied to all sorts of consumer goods, including fast food, video games, and online music sales. It's somewhat similar to work done by researchers at Bristol University, who wrote software that has the potential to predict hit songs.
The big question is, could such a model help a studio avoid disastrous flops, such as last year's John Carter, or 2011's animated Mars needs Moms.