PERFORMANCE EVALUATION OF MACHINE LEARNING CLASSIFICATION TECHNIQUES FOR MOVIE BOX OFFICE SUCCESS PREDICTION
Author(s):
Tasneem Naseem
ISSN:
2349-6002
Cite This Article:
PERFORMANCE EVALUATION OF MACHINE LEARNING CLASSIFICATION TECHNIQUES FOR MOVIE BOX OFFICE SUCCESS PREDICTIONInternational Journal of Innovative Research in Technology(www.ijirt.org) ,ISSN: 2349-6002 ,Volume 5 ,Issue 6 ,Page(s):329-337 ,November 2018 ,Available :IJIRT147267_PAPER.pdf
Keywords:
Movie industry, box office success prediction, machine learning, classification techniques analysis, performance evaluation.
Abstract
With the rapid increase of the multi-billion dollar movie industry, the volume of data that is generated on the internet related to movies is growing at a lightning speed. Machine learning methods have been used by researchers to build classification models. In this report, a variety of machine learning algorithms are used on a movie dataset for multi-class classification. The aim of this paper is to compare the various Machine learning techniques and conduct an analysis on each of their performances. In this report, the selected machine learning methods are Support Vector Machine (SVM), Logistic Regression, Multilayer Perceptron Neural Network and Gaussian Naive Bayes. All these techniques predict an approximate value of the net profit of a movie by examining the historical data collected from varied sources like IMDb, Rotten Tomatoes, Box Office Mojo and Meta Critic. The system predicts box office success based on features that are categorized as pre-released features and post-released features. The performance assessment of these four machine learning methods is done on a movie dataset that contains 755 movies. Among all these techniques, Multilayer Perceptron Neural Network gives a better outcome than the rest.
Article Details
Unique Paper ID: 147267

Publication Volume & Issue: Volume 5, Issue 6

Page(s): 329 - 337
Article Preview & Download




Go To Issue



Call For Paper

Volume 6 Issue 4

Last Date 25 September 2019


About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:8200 61 5067
Email: editor@ijirt.org
Website: ijirt.org

Policies