Paper Info
Title
Prediction Model for Bollywood Movie Success: A Comparative Analysis of Performance of Supervised Machine Learning Algorithms
Abstract
The main purpose of this paper is to do a comparative analysis of prediction models using various machine learning techniques. The models will be used to predict whether a movie will be a hit or flop before it is actually released. The techniques used for comparisons are decision tree, random forest (RF), support vector machine, logistics regression, adaptive tree boosting, and artificial neural network algorithms. The major predictors used in the models are the ratings of the lead actor, IMDb ranking of a movie, music rank of the movie, and total number of screens planned for the release of a movie. The results of most models indicated a reasonable accuracy, ranging from 80 to 90%. However, models based on two techniques, RF and logistic regression, achieved an accuracy of 92%. From the results, the most important predictors of a movie’s success are music rating, followed by its IMDb rating and total screens used for release.
Year
DOI
Venue
2020
10.1007/s12626-019-00040-6
The Review of Socionetwork Strategies
Keywords
DocType
Volume
Prediction model, Bollywood movie prediction, Machine learning, Random forest, Logistic regression
Journal
14
Issue
ISSN
Citations 
1
2523-3173
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
Hemraj Verma100.34
Garima Verma200.34