ABSTRAT:

Movie industry is a multi-billion-dollar industry and now there is a huge amount of data available on the internet related to movie industry. Researchers have developed different machine learning methods which can make good classification models. In this paper, various machine learning classification methods are implemented on our own movie dataset for multi class classification. The main goal of this paper is to conduct performance comparison among various machine learning methods. We choose seven machine learning techniques for this comparison such as Support Vector Machine (SVM), Logistic Regression, Multilayer Perceptron Neural Network, Gaussian Naive Bayes, Random Forest, AdaBoost and Stochastic Gradient Descent (SGD). All of these methods predict an approximate net profit value of a movie by analysing historical data from different sources like IMDb, Rotten Tomatoes, Box Office Mojo and Meta Critic. For all these seven methods, the system predicts a movie box office profit based on some pre-released features and post- released features. This paper analyses the performance assessment of all these seven machine learning techniques based on our own dataset which contains 755 movies. Among these seven algorithms, Multilayer perceptron Neural Network gives better result

EXISTING SYSTEM :

Our dataset contains 755 movies released in between 2012 to 2015. We exclude recent movies as movies’ information are changing every day. Our data sources are IMDb, Rotten Tomatoes, Metacritic and Box Office Mojo. Initially our dataset contains 3183 movies. Most of the features are missing for most of the movies. In many cases, movies budgets are unavailable. After removing those movies, we have data for 800 movies. Among these, budget of some movies were available but other features were not found. After excluding those movies, finally we have a dataset containing all the information of 755 movies. Table I shows the description of all features in our dataset. We use both pre-released and post- released features in our model. Total 15 features are used in our proposed model. Among these 15 features MPAA, cast star power, director star power, no of screen, release month and budget are pre-released features, rest of the features are post released.

EXISTING SYSTEM DISADVANTAGES:

1.LESS ACCURACY

2. LOW EFFICIENCY

PROPOSED SYSTEM :

All these machine learning methods are good as classifiers. Some methods are good for small dataset like ours for example Naive Bayes or Logistic Regression but they are not good for recognizing complex pattern, where Neural Network and other methods like SVM works better. Among these seven methods, MLP Neural Network gives the best result. From 755 movies, our MLP model is able to predict 442 movies correctly and 677 movies if we consider one away prediction. One away prediction means the difference between predicted and target class is 1. For example, suppose a movie is classified as class 5, means it is a blockbuster hit. But the prediction result is class 4. That means our classifier predicted one class less than the true value. For Exact match prediction it will be considered as classification error but if we take one away prediction in consideration, it will be accepted as correct result. We have used two types of features, pre-released features for upcoming movies’ prediction and all features which includes both pre-released and post-released features for prediction after opening weekend. In Fig. 1 and Fig. 2 we can see different performance from all these algorithms considering both exact and one away prediction. Fig 1 shows performance comparison for all features where Fig. 2 is for only pre-released features.

PROPOSED SYSTEM ADVANTAGES:

1.HIGH ACCURACY

2.HIGH EFFICIENCY

SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10

HARDWARE REQUIREMENTS:

 Processor : Core I3
 RAM Capacity : 2 GB
 Hard Disk : 250 GB
 Monitor : 15″ Color
 Mouse : 2 or 3 Button Mouse
 Key Board : Windows 08/10