Bangla movie success prediction using machine learning

Abstract

In present world, machine learning techniques and models are used to predict future. Prediction the movie success before its release has been an immense point of concern for movie industry related all people, especially producer, shake holders and director. Since Bangladeshi movie industry is in threat, they need some kind of assurance that the movie will be successful or not and which factor can improve the profit. The purpose of the work is to make a model which predict Bangla movie success depending on some pre-release factors like actor, actress, director, producer, genre, budget, release date, duration, playback singer, music director that helps Bangladeshi movie industry to determinate specific reason for success so that they can resolve before release. In this model, data mining process and algorithm are applied for movie classification. Decision tree, Random forest, Logistic Regression, Support Vector machine are used and evaluated on this dataset and also focus on to find out some interesting relationship between features using feature engineering techniques and tools. Here, it is supervised classification which classify movie based on IMdb movie rating, where rating are divided into five classes (flop, bad, watchable, super hit and block buster). I visited all Bangladeshi movie related sites to collect data. As Bangladeshi movie data collection is highly unorganized and unavailable, our dataset is not much more longer. This prototype model has been provided much better performance in this challenging scenario.