Predicting the Financial Success of Hollywood Movies Using an Information Fusion Approach

Hollywood has often been called the land of hunches and wild guesses. The uncertainty associated with the predictability of product demand makes the movie business a risky endeavor. Therefore, predicting the box-office receipts of a particular motion picture has intrigued many scholars and industry leaders as a difficult and challenging problem. In this study, with a rather large and feature rich dataset, we explored the use of data mining methods (e.g., artificial neural networks, decision trees and support vector machines along with information fusion based ensembles) to predict the financial performance of a movie at the box-office before its theatrical release. In our prediction models, we have converted the forecasting problem into a classification problem—rather than forecasting the point estimate of box-office receipts; we classified a movie (based on its box-office receipts) into nine categories, ranging from a “flop” to a “blockbuster.” Herein we present our exciting prediction results where we compared individual models to those of the ensamples.