Using Academy Awards to Predict Success of Bollywood Movies using Machine Learning Algorithms

Salman Masih,Imran Ihsan

doi:10.14569/ijacsa.2019.0100257

Abstract

Motion Picture Production has always been a risky and pricey venture. Bollywood alone has released approximately 120 movies in 2017. It is disappointing that only 8% of the movies have made to box office and the remaining 92% failed to return the total cost of production. Studies have explored several determinants that make a motion picture success at box office for Hollywood movies including academy awards. However, same can’t be said for Bollywood movies as there is significantly less research has been conducted to predict their success of a movie. Research also shows no evidence of using academy awards to predict a Bollywood movie’s success. This paper investigates the possibility; does an academy award such as ZeeCine or IIFA, previously won by the actor, playing an important role in movie, impact its success or not? In order to measure, the importance of these academy awards towards a movie’s success, a possible revenue for the movie is predicted using the academy awards information and categorizing the movie in different revenue range classes. We have collected data from multiple sources like Wikipedia, IMDB and BoxOfficeIndia. Various machine-learning algorithms such as Decision Tree, Random Forest, Artificial Neural Networks, Naive Bayes and Bayesian Networks are used for the said purpose. Experiment and their results show that academy awards slightly increase the accuracy making an academy award a non-dominating ingredient of predicating movie’s success on box office.

Highlights

Bollywood releases a couple hundreds of movies every year with anticipation to reciprocate their investment that will only be possible if a movie succeeds
As a result, being a good avenue to be explored, this paper identifies the significance of awards won by leading actors/actresses „Zee Cine‟ and „IIFA‟ for predicting movies success
The most recent work we studied is [5] who have employed the same number of variables with DANN (Dynamic Artificial Neural Network) and few more variables such as production budget, pre-release advertising budget, runtime and seasonality

Summary

Introduction

Bollywood releases a couple hundreds of movies every year with anticipation to reciprocate their investment that will only be possible if a movie succeeds. Every individual has different expectation from a movie, some like comedy others do not and some prefer an actor. Well, making such diverse audience happy or entertaining them is quite challenging problem as entertainment is something that can‟t be quantified at all. A movie industry, Bollywood, must release a movie that is quite entertaining for the audience and will eventually become a success. Not until the film open is darkened theater and sparks fly up between the screen and audience”. This statement has just enlightened us about the complexity involved in predicting a success of a movie. Just to make it clear, success means a financial success at box office

Methods

Results

Conclusion