• Home
  • Submit Paper
  • Check Paper Status
  • Download Certificate/Paper
  • FAQs
  • Contact Us
Email: ijraset@gmail.com
IJRASET Logo
Journal Statistics & Approval Details
Recent Published Paper
Our Author's Feedback
 •  ISRA Impact Factor 7.894       •  SJIF Impact Factor: 7.538       •  Hard Copy of Certificates to All Authors       •  DOI by Crossref for all Published Papers       •  Soft Copy of Certificates- Within 04 Hours       •  Authors helpline No: +91-8813907089(Whatsapp)       •  No Publication Fee for Paper Submission       •  Hard Copy of Certificates to all Authors       •  UGC Approved Journal: IJRASET- Click here to Check     
  • About Us
    • About Us
    • Aim & Scope
  • Editorial Board
  • Impact Factor
  • Call For Papers
    • Submit Paper Online
    • Current Issue
    • Special Issue
  • For Authors
    • Instructions for Authors
    • Submit Paper
    • Download Certificates
    • Check Paper Status
    • Paper Format
    • Copyright Form
    • Membership
    • Peer Review
  • Past Issue
    • Monthly Issue
    • Special Issue
  • Pay Fee
    • Indian Authors
    • International Authors
  • Topics
ISSN: 2321-9653
Estd : 2013
IJRASET - Logo
  • Home
  • About Us
    • About Us
    • Aim & Scope
  • Editorial Board
  • Impact Factor
  • Call For Papers
    • Submit Paper Online
    • Current Issue
    • Special Issue
  • For Authors
    • Instructions for Authors
    • Submit Paper
    • Download Certificates
    • Check Paper Status
    • Paper Format
    • Copyright Form
    • Membership
    • Peer Review
  • Past Issue
    • Monthly Issue
    • Special Issue
  • Pay Fee
    • Indian Authors
    • International Authors
  • Topics

Ijraset Journal For Research in Applied Science and Engineering Technology

  • Home / Ijraset
  • On This Page
  • Abstract
  • Introduction
  • Conclusion
  • References
  • Copyright

Movie Data Analysis and Prediction

Authors: G Pranay Mukund, Kadari Naveen Kumar, Aruna Kumari Kumbhagiri

DOI Link: https://doi.org/10.22214/ijraset.2022.44113

Certificate: View Certificate

Abstract

With the use of Big Data in Cinema Analysis, we are able to assess the model with better precision and eliminate the speculation that typically accompanies the process. The primary goal of this research is to study and create a training data that can forecast the movie\'s income. We used Kaggle\'s information, which includes information on 3000 films, including information on the film\'s title, cast, and budget. Two separate classification methods are used in this project to evaluate, visualise, and train the collection. Regularization and Strange Wooded are the two methods. Algorithms are evaluated based on their RMSE values, and the one with the lowest score is selected. Our last prediction was for film in the collection that did not have a revenue associated with them.

Introduction

I. INTRODUCTION

The term "Big Data" represents a set of documentation that is both large and growing at an exponential rate. Conventional data processing technologies  are unable to store or handle information effectively because it is so massive and complicated. It's a lot of data, but it's also a lot of data. Demand forecasting and other machine learning programs also make use of this technology. Judgement call in the movie industry rely on big data techniques to help respective film firms succeed in a crowded marketplace. With the help of this information, they are able to establish realistic objectives and learn how to achieve them.

II. LITERATURE SURVEY

We have done a lot of literature review on the similar movie revenue prediction projects. We have got some of the existing projects.

Title of the paper 1: Early prediction of movie Box office success. Based on Wikipedia Activity Big Data:

Description: They presented the results of developing a simple statistical model for movie financial performance based on internet user’s cumulative activity data.

By calculating and evaluating the activity level of editors and viewers of the corresponding entry to the movie in Wikipedia, the well – known online encyclopedia, they demonstrated that the success of a movie can be predicted much before its publication.

Title of the paper 2: Sentiment Analysis of Movie Reviews using Machine Learning Techniques.

Description:  It is the analysis which made based on emotions and opinions of any form. Sentiment analysis is also named as opinion mining. This type of methos is useful when we given a content to a particular person as a source to know the sentiment. It is useful to explain the view of a bunch of people or a person. In this sentiment analysis they used techniques like Naïve Bayes, K- Nearest Neighbour and Random Forest.

Title of the paper 3: Movie Success prediction using Data Mining

Description: In this model to predict the success and failure of a movie they used a mathematical model based on some attributes. Some of the attributes used for predicting is genre, director, and budget. To dig out the patterns and trends which will be useful in predicting movie success they used data mining process and applied to movie database. In this model also they used data cleaning and integration process.

Ridge regression and the Randomised forest technique are being used to build a classification model in this project. Main objective is to develop a hardware model that can predict overall sales of a latest film based on available resources, playable demos and classifications and production companies and nations. Kaggle has provided us with a sample of 3000 movies (from 1960 to 2017) with all the important facts on everyone one of them (like cast, crew, budget, popularity, date, Genre etc..). It reduces the financial burden on film producers who plan to make a movie.

III.  METHODOLOGY

Three stages are included in this operation. Among the three stages are Pre-processing, Modeling, and Testing. Each phase has its own internal procedure. This project explains each step in detail. They're as follows:

A. Pre-processing

In order to develop a model, dataset is an essential part of the process. Data collecting, verification, analysis techniques, and manipulating categorical values are just a few of the phases involved in this process. Model adoption and assessment benefit from increased data quality. This stage consists of the following steps:

B. Data Collection

The collection of data Kaggle, a cinematic database, provided the data for this dataset, which spans the years 1960 to 2017. It includes details such as the cast, crew, prequel, popularity, budget, and genre of the film. " The picture of the database is shown below.

C. Data Cleaning

We acquired raw data in the form of a dataset. Everything from the cast to the crew to the movie's success to its genre and subgenres are included. Data preparation is a critical stage in the process of transforming raw data into data that can be used to train models. We are deleting all of the dataset's missing value with this step. The following is an example of what I'm talking

D. Data Analysis

The third phase in this procedure is data analysis. In order to carry out the next stages, it is critical that the data be understood. This stage includes data visualisation. Using a graphical illustration of ordinal data data helps us understand the data better and may lead us to the next step in the process.

Fig-4 shows the top 20 highly interesting films, with the X-axis indicating popularity and the Y-axis indicating the description of the movies. Wonder Women, with a high approval rating of 294, is the most well- liked film of all time.

Below is Fig-6, which displays data on the top 20 highest-grossing blockbusters, with profit (in millions of dollars) plotted on the X-axis and movie titles as seen on the Y- axis. Pirates of something like the Caribbean: On Random person Tides had a budget of 380 million dollars, making it the most expensive film ever made.

With budget(in millions) on the X-axis as well as movie title on the Y-axis, Fig. 7 shows the top 20 biggest producing films of all time.
1316 million dollars is the highest grossing film of all time, making it the most profitable film of all time.

The number of films in various genres is depicted in Fig. 8 below. The X-axis shows the various genres, while the Y-axis shows the total number of films in each category. According to the graph below, there have been 1531 films based mostly on genre of drama produced in theatres.
In Fig-9, the link between Musical styles and Mean average Popularity is depicted. The X-axis represents genre kinds, while the Y-axis depicts the level of popularity for each genre

E. Handling Categorical Values

Attribute data and category values are incompatible with neural network models. So, the categories values must be handled before the model can be implemented. Handles is just like the log - log plot of the values. It aids in the quantitative transformation of attribute variables.

IV. RESULT AND DISCUSSION

Several films with unknown box office grosses were fed into the model once it had been trained successfully. Even though there were a few null values and similar factors like genres, size, and appeal, his model was able to accurately calculate the gross receipts for all 4000 movies included in the data set. Titles like Pokemon: The Rise of Darkrai, Attack of the 50 Walking Woman, Love, Incedies, and Inside Deep Throat are expected to bring in a lot of money. Output.csv contains a total of 4000 films' estimated revenues, which have not been tied to the profit.

Conclusion

We can now estimate the model\'s income more accurately thanks to Big Data in Cinema Analysis, reducing the uncertainty that sometimes accompanies this type of analysis. The primary goal of this research is to study and create a classification model that can forecast the movie\'s income. We used Kaggle\'s dataset, which includes information on 3000 films, including information mostly on film\'s title, cast, and production. Two separate classification methods are used in this project to evaluate, visualise, and train the dataset. Regularization and Randomised Forest are the two methods. Algorithms are evaluated based on their RMSE values, and the one with the lowest score is selected. Last but not least, we\'ve estimated the box office receipts for 4000 pictures in the database that weren\'t previously associated with their box office receipts.

References

[1] Early Prediction of movie Box-Office success. Based on Wikipedia Activity Big Data. Marton Mestyan, Taha Yasseri, Janos Kertesz, 2012. [2] Sentiment Analysis of Movie Reviews using Machine Learning Techniques. Palak Baid, Apoorva Gupta, Neelam chaplot, 2017. [3] Movie Success Prediction using Data Mining. Anantharaman V, Ebin G. Job, Neha sam, Sheryl Maria Sebastian, 2019.

Copyright

Copyright © 2022 G Pranay Mukund, Kadari Naveen Kumar, Aruna Kumari Kumbhagiri. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

IJRASET44113

Download Paper

Authors : G Pranay Mukund

Paper Id : IJRASET44113

Publish Date : 2022-06-11

ISSN : 2321-9653

Publisher Name : IJRASET

DOI Link : Click Here

About Us

International Journal for Research in Applied Science and Engineering Technology (IJRASET) is an international peer reviewed, online journal published for the enhancement of research in various disciplines of Applied Science & Engineering Technologies.

Quick links
  • Privacy Policy
  • Refund & Cancellation Policy
  • Shipping Policy
  • Terms & Conditions
Quick links
  • Home
  • About us
  • Editorial Board
  • Impact Factor
  • Submit Paper
  • Current Issue
  • Special Issue
  • Pay Fee
  • Topics
Journals for publication of research paper | Research paper publishers | Paper publication sites | Best journal to publish research paper | Research paper publication sites | Journals for paper publication | Best international journal for paper publication | Best journals to publish papers in India | Journal paper publishing sites | International journal to publish research paper | Online paper publishing journal

© 2022, International Journal for Research in Applied Science and Engineering Technology All rights reserved. | Designed by EVG Software Solutions