Once again a computer takes hours to calculate the obvious…
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.
The results of the study showed that 37 percent of the time the network accurately predicted which category the film fell into, and 75 percent of the time was within one category of the correct answer. Among the correct predictions: “Spider-Man” and “Shrek” were rated as blockbusters, while “Waking Up in Reno” and “Running Free” were pegged as flops.
Does this computer make a sound when it comes up with these astounding predictions? If it doesn’t, may I suggest “Doy!”?
UPDATE 10/15/2005: Scott Kirsner at CinemaTech has his own criticisms of the predictator.
[S]eems like you could lose a lot of money on the 63 percent of movies where the computer can’t accurately predict. And some of the criteria the system uses, like number of theaters a film opens in, and competition from other films, aren’t things that studio chiefs know when they’re considering whether to green-light a film and commit millions of dollars.