A comparative study of different classifiers for blockbuster movies / Masih Mikhak

Masih , Mikhak (2019) A comparative study of different classifiers for blockbuster movies / Masih Mikhak. Masters thesis, University of Malaya.

[img] PDF (The Candidate's Agreement)
Restricted to Repository staff only

Download (197Kb)
    PDF (Thesis M.A)
    Download (1251Kb) | Preview


      The purpose of this study is to investigate the blockbuster movie prediction using machine learning techniques. Predicting blockbuster movie success has been proven to be challenging and difficult and there is no effective research to prove which machine learning classifier and feature combination would provide most accurate prediction. Statistical analysis as well as operational researches are used to achieve best possible prediction, considering the strength and weakness of all these researches highlight the objectives of this research. This research aims to present and compare which different machine learning classifiers produce most accurate prediction result and determine which feature combination can predict with high accuracy. In this study, four machine leaning classifiers and combination of features were applied to over 400 movies to find out which classifier gives the highest accuracy. The result of this research represent that the K-NN classifier provide higher accuracy which by comparing the result by actual movies success in Box-office it clearly emphasis the contribution of this research.

      Item Type: Thesis (Masters)
      Additional Information: Dissertation (M.A.) – Faculty of Computer Science & Information Technology, University of Malaya, 2019.
      Uncontrolled Keywords: Blockbuster prediction; Machine learning techniques; Machine learning classifier
      Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
      Divisions: Faculty of Computer Science & Information Technology
      Depositing User: Mr Mohd Safri Tahir
      Date Deposited: 07 Jan 2020 06:44
      Last Modified: 18 Jan 2020 10:35
      URI: http://studentsrepo.um.edu.my/id/eprint/10706

      Actions (For repository staff only : Login required)

      View Item