Predicting box-office success of motion pictures with neural networks

Ramesh Sharda, Dursun Delen

Research output: Contribution to journalArticle

137 Citations (Scopus)

Abstract

Predicting box-office receipts of a particular motion picture has intrigued many scholars and industry leaders as a difficult and challenging problem. In this study, the use of neural networks in predicting the financial performance of a movie at the box-office before its theatrical release is explored. In our model, the forecasting problem is converted into a classification problem-rather than forecasting the point estimate of box-office receipts, a movie based on its box-office receipts in one of nine categories is classified, ranging from a 'flop' to a 'blockbuster.' Because our model is designed to predict the expected revenue range of a movie before its theatrical release, it can be used as a powerful decision aid by studios, distributors, and exhibitors. Our prediction results is presented using two performance measures: average percent success rate of classifying a movie's success exactly, or within one class of its actual performance. Comparison of our neural network to models proposed in the recent literature as well as other statistical techniques using a 10-fold cross validation methodology shows that the neural networks do a much better job of predicting in this setting.

Original languageEnglish
Pages (from-to)243-254
Number of pages12
JournalExpert Systems with Applications
Volume30
Issue number2
DOIs
StatePublished - 1 Feb 2006
Externally publishedYes

Fingerprint

Motion pictures
Neural networks
Studios
Industry

Keywords

  • Box-office receipts
  • CART
  • Forecasting
  • Logistic regression
  • Motion pictures
  • Neural networks
  • Prediction
  • Sensitivity analysis

Cite this

@article{91d9f4b861f145289d2a75d83c9846df,
title = "Predicting box-office success of motion pictures with neural networks",
abstract = "Predicting box-office receipts of a particular motion picture has intrigued many scholars and industry leaders as a difficult and challenging problem. In this study, the use of neural networks in predicting the financial performance of a movie at the box-office before its theatrical release is explored. In our model, the forecasting problem is converted into a classification problem-rather than forecasting the point estimate of box-office receipts, a movie based on its box-office receipts in one of nine categories is classified, ranging from a 'flop' to a 'blockbuster.' Because our model is designed to predict the expected revenue range of a movie before its theatrical release, it can be used as a powerful decision aid by studios, distributors, and exhibitors. Our prediction results is presented using two performance measures: average percent success rate of classifying a movie's success exactly, or within one class of its actual performance. Comparison of our neural network to models proposed in the recent literature as well as other statistical techniques using a 10-fold cross validation methodology shows that the neural networks do a much better job of predicting in this setting.",
keywords = "Box-office receipts, CART, Forecasting, Logistic regression, Motion pictures, Neural networks, Prediction, Sensitivity analysis",
author = "Ramesh Sharda and Dursun Delen",
year = "2006",
month = "2",
day = "1",
doi = "10.1016/j.eswa.2005.07.018",
language = "English",
volume = "30",
pages = "243--254",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Ltd",
number = "2",

}

Predicting box-office success of motion pictures with neural networks. / Sharda, Ramesh; Delen, Dursun.

In: Expert Systems with Applications, Vol. 30, No. 2, 01.02.2006, p. 243-254.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predicting box-office success of motion pictures with neural networks

AU - Sharda, Ramesh

AU - Delen, Dursun

PY - 2006/2/1

Y1 - 2006/2/1

N2 - Predicting box-office receipts of a particular motion picture has intrigued many scholars and industry leaders as a difficult and challenging problem. In this study, the use of neural networks in predicting the financial performance of a movie at the box-office before its theatrical release is explored. In our model, the forecasting problem is converted into a classification problem-rather than forecasting the point estimate of box-office receipts, a movie based on its box-office receipts in one of nine categories is classified, ranging from a 'flop' to a 'blockbuster.' Because our model is designed to predict the expected revenue range of a movie before its theatrical release, it can be used as a powerful decision aid by studios, distributors, and exhibitors. Our prediction results is presented using two performance measures: average percent success rate of classifying a movie's success exactly, or within one class of its actual performance. Comparison of our neural network to models proposed in the recent literature as well as other statistical techniques using a 10-fold cross validation methodology shows that the neural networks do a much better job of predicting in this setting.

AB - Predicting box-office receipts of a particular motion picture has intrigued many scholars and industry leaders as a difficult and challenging problem. In this study, the use of neural networks in predicting the financial performance of a movie at the box-office before its theatrical release is explored. In our model, the forecasting problem is converted into a classification problem-rather than forecasting the point estimate of box-office receipts, a movie based on its box-office receipts in one of nine categories is classified, ranging from a 'flop' to a 'blockbuster.' Because our model is designed to predict the expected revenue range of a movie before its theatrical release, it can be used as a powerful decision aid by studios, distributors, and exhibitors. Our prediction results is presented using two performance measures: average percent success rate of classifying a movie's success exactly, or within one class of its actual performance. Comparison of our neural network to models proposed in the recent literature as well as other statistical techniques using a 10-fold cross validation methodology shows that the neural networks do a much better job of predicting in this setting.

KW - Box-office receipts

KW - CART

KW - Forecasting

KW - Logistic regression

KW - Motion pictures

KW - Neural networks

KW - Prediction

KW - Sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=28544450051&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2005.07.018

DO - 10.1016/j.eswa.2005.07.018

M3 - Article

AN - SCOPUS:28544450051

VL - 30

SP - 243

EP - 254

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 2

ER -