Forecasting financial success of hollywood movies a comparative analysis of machine learning methods

Dursun Delen, Ramesh Sharda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Forecasting financial success of a particular movie has intrigued many scholars and industry leaders as a worthy but challenging problem. In this study, we explore the use of machine learning methods to forecast the financial performance of a movie at the box-office before its theatrical release. In our models, we convert the forecasting problem into a multinomial classification problem-rather than forecasting the point estimate of box-office receipts; we classify a movie based on its box-office receipts in one of nine categories, ranging from a "flop" to a "blockbuster." Herein, we present our comparative prediction results along with variable importance measures (using sensitivity analysis on trained prediction models).

Original languageEnglish
Title of host publicationICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics
Pages653-656
Number of pages4
StatePublished - 26 Oct 2012
Externally publishedYes
Event9th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2012 - Rome, Italy
Duration: 28 Jul 201231 Jul 2012

Publication series

NameICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics
Volume1

Conference

Conference9th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2012
CountryItaly
CityRome
Period28/07/1231/07/12

Fingerprint

Learning systems
Sensitivity analysis
Industry

Keywords

  • Box-office receipts
  • Hollywood
  • Machine learning
  • Neural networks
  • Prediction
  • Sensitivity analysis

Cite this

Delen, D., & Sharda, R. (2012). Forecasting financial success of hollywood movies a comparative analysis of machine learning methods. In ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics (pp. 653-656). (ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics; Vol. 1).
Delen, Dursun ; Sharda, Ramesh. / Forecasting financial success of hollywood movies a comparative analysis of machine learning methods. ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics. 2012. pp. 653-656 (ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics).
@inproceedings{8e2ac6e5cd0c4a148b68012844e6a6b2,
title = "Forecasting financial success of hollywood movies a comparative analysis of machine learning methods",
abstract = "Forecasting financial success of a particular movie has intrigued many scholars and industry leaders as a worthy but challenging problem. In this study, we explore the use of machine learning methods to forecast the financial performance of a movie at the box-office before its theatrical release. In our models, we convert the forecasting problem into a multinomial classification problem-rather than forecasting the point estimate of box-office receipts; we classify a movie based on its box-office receipts in one of nine categories, ranging from a {"}flop{"} to a {"}blockbuster.{"} Herein, we present our comparative prediction results along with variable importance measures (using sensitivity analysis on trained prediction models).",
keywords = "Box-office receipts, Hollywood, Machine learning, Neural networks, Prediction, Sensitivity analysis",
author = "Dursun Delen and Ramesh Sharda",
year = "2012",
month = "10",
day = "26",
language = "English",
isbn = "9789898565211",
series = "ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics",
pages = "653--656",
booktitle = "ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics",

}

Delen, D & Sharda, R 2012, Forecasting financial success of hollywood movies a comparative analysis of machine learning methods. in ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics. ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics, vol. 1, pp. 653-656, 9th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2012, Rome, Italy, 28/07/12.

Forecasting financial success of hollywood movies a comparative analysis of machine learning methods. / Delen, Dursun; Sharda, Ramesh.

ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics. 2012. p. 653-656 (ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Forecasting financial success of hollywood movies a comparative analysis of machine learning methods

AU - Delen, Dursun

AU - Sharda, Ramesh

PY - 2012/10/26

Y1 - 2012/10/26

N2 - Forecasting financial success of a particular movie has intrigued many scholars and industry leaders as a worthy but challenging problem. In this study, we explore the use of machine learning methods to forecast the financial performance of a movie at the box-office before its theatrical release. In our models, we convert the forecasting problem into a multinomial classification problem-rather than forecasting the point estimate of box-office receipts; we classify a movie based on its box-office receipts in one of nine categories, ranging from a "flop" to a "blockbuster." Herein, we present our comparative prediction results along with variable importance measures (using sensitivity analysis on trained prediction models).

AB - Forecasting financial success of a particular movie has intrigued many scholars and industry leaders as a worthy but challenging problem. In this study, we explore the use of machine learning methods to forecast the financial performance of a movie at the box-office before its theatrical release. In our models, we convert the forecasting problem into a multinomial classification problem-rather than forecasting the point estimate of box-office receipts; we classify a movie based on its box-office receipts in one of nine categories, ranging from a "flop" to a "blockbuster." Herein, we present our comparative prediction results along with variable importance measures (using sensitivity analysis on trained prediction models).

KW - Box-office receipts

KW - Hollywood

KW - Machine learning

KW - Neural networks

KW - Prediction

KW - Sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=84867700770&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84867700770

SN - 9789898565211

T3 - ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics

SP - 653

EP - 656

BT - ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics

ER -

Delen D, Sharda R. Forecasting financial success of hollywood movies a comparative analysis of machine learning methods. In ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics. 2012. p. 653-656. (ICINCO 2012 - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics).