Comparative Analysis for Prediction of Success of Bollywood Movie

Abstract

In terms of Film Production, Indian Cinema is one of the largest Film Industry where more than thousands of movies released each year. The large part of Indian Cinema is Bollywood which is multi-million dollar industry. So, this Paper attempts to predict whether the upcoming Bollywood Movie would be Blockbuster, Superhit, Hit, Average or Flop. For this Data Mining techniques (classification and prediction) will be applied. Data Mining is the process of discovering different patterns from large data sets and from that various relationships are also discovered to solve various problems which come in business and helps to predict the forthcoming trends. The main difference between classification and prediction is that the classification predicts the definitive categorical labels and prediction techniques predicts the continuous values. Every big business is engaging a large amount of data so after analyzing them the company can define different strategies to achieve business aims and profits. For these, there are various techniques available with different data visualization tools such as Microsoft Power BI, Tableau, Logi Analytics, Orange, etc. To make classifier or prediction model first step is learning stage in which we need to give the training data set to train the model by applying some technique or algorithm and after that different rules are generated which helps to make a model and predict future trends in different types of organizations. All the techniques related to classification and Prediction such as Decision Tree, Naïve Bayes, Logistic Regression, Adaboost, and KNN will be applied and try to find out efficient and effective results. These Algorithms would be applied in Orange. The orange tool is Open-Source software which incorporates Data Mining, Machine Learning and Data Visualization which makes our work easy and everything in one place. All these functionalities can be applied with GUI Based workflows available with various categories such as data, Visualize, Model, Evaluate. This paper focuses on Comparative Analysis that would be performed based on different parameters such as Accuracy, Confusion Matrix to identify the Best possible model for predicting the movie Success. This Prediction can help Production Houses for Advertisement Propaganda and they can plan their costs and by assuring these factors they can make the movie more profitable. By this, they can also decide as which is the best time to release the movie according to the predicted success rate defined by mode to gain higher benefits.

Keywords: Decision Tree, Data Mining, Prediction