Predicting Hollywood's Blockbusters

from the good-luck-with-that dept

A professor from Oklahoma State University says he’s developed a computer program that can predict if a movie will be a box-office hit before it’s even been made. The program judges films on seven criteria, including its rating, genre, cast, special effects, whether it’s a sequel, on how many screens it will open and its competition on release, then puts it into one of seven categories ranging from flop to blockbuster, depending on how much money it’s predicted to make. We’re skeptical of the system, and not just because it’s accurate only about 35% of the time, or because it doesn’t take a movie’s actual quality into consideration. If the professor wants to predict the future based on past events, so can we. Two years ago we wrote about a similar computer for pop music, which, judging by the amount of crap still on the radio, hasn’t worked out. It’s hard to see the movie computer doing any better, even though one studio is reportedly in talks to develop it further.

Rate this comment as insightful
Rate this comment as funny
You have rated this comment as insightful
You have rated this comment as funny
Flag this comment as abusive/trolling/spam
You have flagged this comment
The first word has already been claimed
The last word has already been claimed
Insightful Lightbulb icon Funny Laughing icon Abusive/trolling/spam Flag icon Insightful badge Lightbulb icon Funny badge Laughing icon Comments icon

Comments on “Predicting Hollywood's Blockbusters”

Subscribe: RSS Leave a comment
MadJeff says:

the full quote

The actual quote, from the article is:

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.

So 75% of the time the model will predict the boxoffice results within $60 mil, and 37% of the time the results will be within $20 mil. Sounds pretty useful to me for ballparking purposes.

Mark (profile) says:


You know where this could be useful? If it delivers the message that derivative crap will fail at the box office, and one studio head believes the message and instructs his employees to work on better, more original material. Even if the program is a piece of crap, it could still prove beneficial if it forces Hollywood out of one or more of its bad habits.

Newob says:

Movie-prediction movie

One way to test it would be to try a whole lot of awful movies and see what it makes of them.

On the other hand, why not a movie about a movie designed by the movie-success predictor? “According to this program, this movie should be a smash hit!” Then the program can be the protagonist (or the antagonist) of every sequel! How many people were lured by the program into making bad movies, deliberately by the military-industrial-entertainment complex?

Add Your Comment

Your email address will not be published. Required fields are marked *

Have a Techdirt Account? Sign in now. Want one? Register here

Comment Options:

Make this the or (get credits or sign in to see balance) what's this?

What's this?

Techdirt community members with Techdirt Credits can spotlight a comment as either the "First Word" or "Last Word" on a particular comment thread. Credits can be purchased at the Techdirt Insider Shop »

Follow Techdirt

Techdirt Daily Newsletter

Techdirt Deals
Techdirt Insider Discord
The latest chatter on the Techdirt Insider Discord channel...