TRAP@NCI

Prediction Models for Box Office Revenue before Theatrical Release of Movies

Naik, Altamash (2017) Prediction Models for Box Office Revenue before Theatrical Release of Movies. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (2MB) | Preview

Abstract

This research project proposes to develop prediction models in the entertainment domain. There Prediction Models for Box Office Revenue before Theatrical Release of Movies is a model that has been developed using the parameters of social media platforms and necessary attributes of the movies that influence the success of the movie. The data encapsulating these essential attributes for predictive analysis is extracted from Data repository and using R programming language. The research highlights the impact of predictive data analysis in decision making in film making industry. Machine learning techniques like Decision Tree, Logistic regression, Nave Bayes, Random Forest and SVM are implemented for designing predictive models that utilises this information and determines the probability of the movie using Rapid Miner. The attained results are evaluated and visualized. Graphical representations of these results are implemented in Tableau and Rapid Miner. The model provides great insights for the investors to identify the key fundamentals that are influential in the success of the movie from initial pre-production stages to the release of the movie covering all the major aspects for marketing and promotions.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Film Industry
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 28 Aug 2018 14:55
Last Modified: 28 Aug 2018 14:55
URI: http://trap.ncirl.ie/id/eprint/3098

Actions (login required)

View Item View Item