Will the 3-hour special-effects-loaded remake of King Kong be a box office smash or a complete turkey? For movie producers, getting such questions right can be worth millions, and now they have a computer system to help them work it out before a film is even made.
The idea is based on the findings of entertainment industry market researcher Edith Bodnar, who while at the University of Wisconsin in Madison in 1998 came up with the idea of training a type of software package called an artificial neural network to learn the key factors that influence a movie鈥檚 likely success. Now the computer expert Bodnar asked to investigate the idea, Ramesh Sharda of Oklahoma State University in Stillwater, has reported encouraging results of a five year trial in the journal Expert Systems with Applications (vol 30, p 243).
Using data on 834 movies released between 1998 and 2002, Sharda found that the neural network can judge a film based on seven key parameters: the 鈥渟tar value鈥� of the cast, the movie鈥檚 age rating, the time of release against that of competitive movies, the film鈥檚 genre, the degree of special effects used, whether it is a sequel or not, and the number of screens it is expected to open in. This allowed it to place a movie in one of nine categories, ranging from 鈥渇lop鈥� (total takings less than $1 million) to 鈥渂lockbuster鈥� (over $200 million).
Advertisement
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 鈥減owerful decision aid鈥�, Sharda says.
Bodnar is now in talks with a 鈥渕ajor Hollywood studio鈥� about further development of the software.
