final report.pdf

1
MOVIE RECOMMENDATION SYSTEM
A MINOR PROJECT
Submitted in Partial Fulfillment of the Requirement for the Award of the Degree of
BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE ENGINEERING
SUBMITTED TO – Dr. PRASHANT SHRIVASTAVA and PROF. PRAVEEN BHARGAVA
Rajiv Gandhi Proudyogiki Vishwavidyalaya, Bhopal (M.P.)
SUBMITTED BY
ANANYA BAGHEL (0176CS201031)
ROHIT SONI (0176CS201145)
RITIKA MAMTANI (0176CS201144)
(Lakshmi Narain College of Technology Excellence, Bhopal (M.P.), India)
UNDER THE SUPERVISION OF
Dr. PRASHANT SHRIVASTAVA and PROF. PRAVEEN BHARGAVA
Department of Computer Science & Engineering
Lakshmi Narain College of Technology Excellence, Bhopal (M.P.), India

2
MOVIE RECOMMENDATION SYSTEM
A Movie Recommendation System is a fancy way to describe a process that tries to predict
your preferred items based on your or people similar to you.
In layman’s terms, we can say that a Recommendation System is a tool designed to
predict/filter the items as per the user’s behaviour.
From a user’s perspective, they are catered to fulfill the user’s needs in the shortest time
possible. For example, the type of content you watch on Netflix or Hulu. A person who likes
to watch only Korean drama will see titles related to that only but a person who likes to
watch Action-based titles will see that on their home screen.

3
(Approved by AICTE, New Delhi & Affiliated to RGPV, Bhopal)
Kalchuri Nagar, Raisen Road, Bhopal (M.P.)
Email: lnctebhopal@lnctgroup.in, Website: www.lnctgroup.in
Phone: +91-7553985300, 7553985301, 7553985302, 7553985303
CANDIDATE’S DECLARATION
We, ANANYA BAGHEL, ROHIT SONI, RITIKA MAMTANI, students of Bachelor of Technology,
computer science Engineering, Lakshmi Narain College of Technology Excellence, Bhopal hereby
declare that the work presented in the project entitled “MOVIE RECOMMENDATION SYSTEM” is
outcome of our own bona-fide work, which is correct to the best of our knowledge and this work has been
carried out taking care of Engineering Ethics. The work presented does not infringe any previous work and
has not been submitted to any University for the award of any degree.
The project entitled “MOVIE RECOMMENDATION SYSTEM” being submitted by ANANYA BAGHEL,
ROHIT SONI AND RITIKA MAMTANI has been examined by us and is hereby approved for the award of
degree “Bachelor of Technology in Computer Science Engineering”, for which it has been submitted. It is
understood that by this approval the undersigned do not necessarily endorse or approve any statement made,
opinion expressed or conclusion drawn therein, but approve the project only for the purpose for which it has
been submitted.
Student Name: ANANYA BAGHEL
Enrollment No.: 0176CS201031
Student Name: ROHIT SONI
Student Name: RITIKA MAMTANI

4
Phone: +91-7553985300, 7553985301, 7553985302, 7553985303
CERTIFICATE
This is to certify that the project entitled “Movie Recommendation System” is the bona-fide work carried
out independently by ANANYA BAGHEL, ROHIT SONI, RITIKA MAMTANI, student of Bachelor of
Technology, Department of Computer Science Engineering from Rajiv Gandhi Prodyogiki Vishwavidyalaya,
Bhopal.
In the partial fulfillment of the requirement for the award of the degree of Bachelor of Technology, and this
project has not formed previously the basis for the award of any degree, diploma, associate ship, fellowship
or any other similar title according to our knowledge.
SUPERVISED BY:
Dr. Prashant Shrivastava
(Department of CSE)
LNCTE, Bhopal
Prof. Praveen Bhargava
(Department of C.S.E)
LNCTE, BHOPAL
APPROVED BY:
Dr. Megha Kamble
(Head, Department of CSE)
LNCTE, Bhopal
FORWARDED BY:
Dr. Anil Kumar Saxena
Principal
LNCTE, Bhopal

5
Phone: +91-7553985300, 7553985301, 7553985302, 7553985303
ACKNOWLEDGEMENT
At the outset, we would like to link to thank the Almighty who made all the things possible. Writing this
project report would not have been possible without the support of several people whom we need to
wholeheartedly thank. A special thanks to “Dr. Megha Kamble” Professor and Head, Department of Computer
Science and Engineering, LNCTE, Bhopal who helped us in completing the project and exchanged her
interesting ideas thoughts and made this project possible.
We are equally grateful to Dr. Anil Kumar Saxena, principal, LNCTE for providing all the necessary
resources to carry out this project work. We would like to thank all staff members of L.N.C.T.E. – CSE and
friends, for their moral and psychological support.
Student Name: ANANYA BAGHEL
Student Name: ROHIT SONI
Student Name: RITIKA MAMTANI

6
ABSTRACT
Each of us needs entertainment to recharge our spirits and energy in this fast-paced world. Our confidence
for work is restored by entertainment, and we work more ardently as a result. We can watch our favorite
movies or listen to our favorite music to reenergize ourselves. Since finding chosen movies will take more
and more time, which one cannot afford to waste, we can use more reliable movie recommendation
algorithms to watch good movies online. In this paper, a hybrid approach that combines content-based
filtering, collaborative filtering, using Support Vector Machine as a classifier, and genetic algorithm is
presented in the proposed methodology. Comparative results are shown, showing that the proposed approach
shows an improvement in the accuracy, quality, and scalability of the movie recommendation system than
the pure approaches in three areas: accuracy, quality, and scalability. The advantages of both approaches are
combined in a hybrid strategy, which also seeks to minimize their negative aspects.

7
TABLE OF CONTENTS
1. Candidate’s Declaration
2. Certificate
3. Acknowledgement
4. Abstract
5. Table of contents
6. Introduction (Chapter – 1)
6.1 Relevance of the Project
6.2 Problem Statement
6.3 Objective
6.4 Scope of the Project
6.5 Methodology
7. Detailed Study of Recommendation Systems (Chapter – 2)
7.1 Types of Recommendation System
8. System Requirements Specification (Chapter – 3)
8.1 Hardware Requirements
8.2 Software Specification
8.3 Software Requirements
8.3.1 Anaconda distribution
8.3.2 NumPy
8.3.3 Pandas
8.3.4 Streamlit
8.3.5 Requests
9. System Analysis and Design (Chapter – 4)
9.1 System Architecture of Proposed System
9.2 Dataflow
10. Implementation (Chapter – 5)
10.1 Cosine similarity
10.2 Experimental Setup
10.2.1 Code: Front-end (PyCharm)
10.2.2 Code: Back-end (Jupyter Notebook)
11. Results and Discussion (Chapter – 6)
12. Testing (Chapter – 7)
13. Conclusion and Future Scope (Chapter – 8)
13.1 Conclusion
13.2 Future Scope
14. Bibliography (Chapter – 9)

8
Chapter 1:
INTRODUCTION
1.1 Relevance Of The Project
A recommendation system, sometimes known as a recommendation engine, is a paradigm for information
filtering that aims to anticipate user preferences and offer suggestions in accordance with these preferences.
These technologies are now widely used in a variety of industries, including those that deal with utilities,
books, music, movies, television, apparel, and restaurants. These systems gather data on a user's preferences
and behavior, which they then employ to enhance their future suggestions.
There are many various kinds of movies, such as those meant for amusement, those meant for teaching,
children's animation movies, horror movies, and action movies. Watching movies is relaxing. Distinguished
by their various genres, such as humor, suspense, animation, action, etc. Another approach to differentiate
between movies is to look at their release year, language, director, etc. When watching movies online, there
are many to choose from in our list of top picks. We may find our favourite movies among all of these
different kinds of movies with the aid of movie recommendation systems, which saves us the stress of
having to spend a lot of time looking for our preferred movies. As a result, it is essential that the system for
suggesting movies to us is very trustworthy and gives us recommendations for the films that are either most
similar to or identical to our tastes.
Recommendation systems are being used by a lot of businesses to improve customer interaction and the
purchasing experience. The most significant advantages of recommendation systems are client happiness and
income.

9
1.2 2 Problem Statement
The goal of the project is to recommend top 5 similar movies to the user according to the what the he or she
wants to watch which also saves up a lot of time for the user.
Also, Providing related content out of the relevant and irrelevant collection of items to users of online
service providers.

10
1.3 Objective of the Project
1. Improving the Accuracy of the recommendation system
2. Improve the Quality of the movie Recommendation system
3. Improving the Scalability.
4. Enhancing the user experience.

11
1.4 Scope of the Project
The objective of this project is to provide accurate movie recommendations to users. The goal of the project
is to improve the quality of movie recommendation system, such as accuracy, quality and scalability of
system than the pure approaches. This is done using content based filtering. To eradicate the overload of the
data, recommendation system is used as information filtering tool in social networking sites. Hence, there is
a huge scope of exploration in this field for improving scalability, accuracy and quality of movie
recommendation systems Movie Recommendation system is very powerful and important system.

12
1.5 Methodology used for Movie Recommendation
Content-Based Filtering:
Content-based filtering methods are done based on user characteristics. This method is used in situations
where data is known on an item such as name, location, or description and not on the user. It predicts the
items based on user’s information and completely ignores contributions from other users as with the case of
collaborative techniques. It uses the data that is provided by the user either explicitly or implicitly. When the
user provides more content-based filtering mechanisms actions on the recommendations such as content-
based recommender the engine becomes more and more accurate.
Agile Methodology:
1. Collecting the data sets:
Collecting all the required data set from Kaggle web site in this project we require movie.csv, ratings.csv,
users.csv.
2. Data Analysis:
Make sure that that the collected data sets are correct and analyzing the data in the csv files i.e. checking
whether all the column Felds are present in the data sets.
3. Algorithms: in our project we have only two algorithms one is cosine similarity and other is single valued
decomposition are used to build the machine learning recommendation model.
4. Training and Testing the model: once the implementation of algorithm is completed. we have to train
the model to get the result. We have tested it several times the model is recommend different set of movies
to different users.
5. Improvements in the project: In the later stage we can implement different algorithms and methods for
better recommendation.

13
Chapter 2:
Detailed Study of Recommendation Systems
2.1 Types of Recommendation System
Systems that propose things, create playlists, find matches, and do much more are known as recommender
systems. User-item interactions and characteristic information are key components of recommender systems'
operation. Information about the user and the items constitutes characteristic information, whereas
information about user-item interactions includes ratings, the volume of purchases, user likes, and many
other things. Based on this, a collaborative filtering, content-based filtering, or hybrid filtering approach can
be used to create the recommendation system.
Collaborative Filtering:
Filtering by collaboration. This algorithm finds people who share similar tastes and uses their feedback to
suggest the same to a different person who has those interests. Utilizing data from rating profiles for various
persons or things, it creates suggestions. It has been incorporated into a variety of programmes, including
Spotify, Netflix, and YouTube. It is a common strategy and a component of the hybrid system.
Content-Based Filtering:
User attributes are used to inform content-based filtering techniques. When information about an item, such
as its name, location, or description, but not about the user, is known, this method is employed. As with
collaborative approaches, it entirely disregards the input from other users and guesses the things based on the
user's information. It makes either explicit or implicit use of the user-provided data. The accuracy of the
engine increases as more content-based filtering mechanisms, such as content-based recommenders, are
provided by the user.
Hybrid Approach:
Combining collaborative filtering with content-based filtering or any other strategy is known as a hybrid
approach. By establishing independent forecasts for content-based and collaborative-based approaches
before integrating them, hybrid systems can be put into practice. It improves the recommender systems'
performance and accuracy.
This project is made with the approach of Content-Based Filtering.

14
Chapter 3:
System Requirements Specification
This chapter involves both the hardware and software requirements needed for the project and detailed
explanation of the specifications.
3.1 Hardware Requirements
1. A PC with Windows/Linux OS
2. Processor with 1.7-2.4gHz speed
3. Minimum of 8gb RAM
4. 2gb Graphic card
3.2 Software Specification
1. Anaconda distribution package (Jupyter notebook)
2. Anaconda distribution package (PyCharm Editor)
3. Python libraries- Streamlit, Numpy, Pandas, Requests

15
3.3 Software Requirements
3.3.1 Anaconda distribution:
Anaconda is a free and open-source distribution of the Python programming languages for
scientific computing (data science, machine learning applications, large-scale data
processing, predictive analytics, etc.), that aims to simplify package management system and
deployment. Package versions are managed by the package management system. The
anaconda distribution includes data-science packages suitable for Windows, Linux and
MacOS.3
3.3.2 NumPy:
NumPy is a general-purpose array-processing package. It provides a high-performance
multidimensional array object, and tools for working with these arrays. It is the fundamental
package for scientific computing with Python.
3.3.3 Pandas:
Pandas is one of the most widely used python libraries in data science. It provides high-
performance, easy to use structures and data analysis tools. Unlike NumPy library which
provides objects for multi-dimensional arrays, Pandas provides in-memory 2d table object
called Data frame.
3.3.4 Streamlit:
Streamlit is an open-source Python library that makes it easy to create and share beautiful,
custom web apps for machine learning and data science. In just a few minutes you can build
and deploy powerful data apps.

16
3.3.5 Requests:
The requests library is the de facto standard for making HTTP requests in Python. It abstracts
the complexities of making requests behind a beautiful, simple API so that you can focus on
interacting with services and consuming data in your application.

17
Chapter 4:
System Analysis and Design
4.1 System Architecture of Proposed System:
Based on content based filtering approaches used in the project, each search will recommend a set of 5
movies to a particular user. When the user will search for a movie, top 5 most similar movies in terms of
similar content will get recommended to the user.

18
4.2 Dataflow:
Initially load the data sets that are required to build a model the data set that are required in this project are
movies.csv, ratinfg.csv, users.csv all the data sets are available in the Kaggle.com. Preprocessing of the data
set will take place and then by applying content-based filtering, users will get recommended top 5 most
similar movies according to their search.

19
Chapter 5:
IMPLEMENTATION
Recommending movies to users can be done in multiple ways using content-based filtering and collaborative
filtering approaches. Content-based filtering approach primarily focuses on the item similarity i.e., the
similarity in movies, whereas collaborative filtering focuses on drawing a relation between different users of
similar choices in watching movies.
Based on the plot of a movie that was watched by the user in the past, movies with a similar plot can be
recommended to the user. This approach comes under content-based filtering as the recommendations are
done only based on the user’s past activity.
Dataset used: A kaggle dataset which was scraped from wikipedia and contains plot summary of movies.
5.1 Cosine Similarity:
The movie plots are transformed as vectors in a geometric space. Therefore, the angle between two vectors
represents the closeness of those two vectors. Cosine similarity calculates similarity by measuring the cosine
of the angle between two vectors.
5.2 Vectorization:
Vectorization is used to speed up the Python code without using loop. Using such a function can help in
minimizing the running time of code efficiently. Various operations are being performed over vector such
as dot product of vectors which is also known as scalar product as it produces single output, outer products
which results in square matrix of dimension equal to length X length of the vectors, Element wise
multiplication which products the element of same indexes and dimension of the matrix remain unchanged.

20
5.2 Experimental Setup:
5.2.1 Code: Front-end (PyCharm):
In this project we have used popular front-end web framework (PyCharm) to build an interactive
user interface.

22
5.2.2 Code: back-end (Jupyter notebook): For backend, we used Jupyter notebook to generate a local host
Api and the resultant Api is fetched in front to display the result.
We used python language for making our movie recommendation system.

24
Chapter 6:
Result and Discussions
Our movie recommendation system is based on content based filtering. Its few advantages and
disadvantages are listed below –
6.1 Advantages
 The model doesn't need any data about other users, since the recommendations are specific to this
user. This makes it easier to scale to a large number of users.
 The model can capture the specific interests of a user, and can recommend niche items that very few
other users are interested in.
6.2 Disadvantages
 Since the feature representation of the items are hand-engineered to some extent, this technique
requires a lot of domain knowledge. Therefore, the model can only be as good as the hand-
engineered features.
 The model can only make recommendations based on existing interests of the user. In other words,
the model has limited ability to expand on the users' existing interests.

25
Screenshots of the result –

27
Chapter 7:
TESTING
The goal of system testing, which consists of a variety of tests, is to completely exercise the
computer-based system. Despite the fact that each test has a distinct objective, they all aim to ensure
that all system components have been correctly integrated and carry out their assigned functions. The
testing procedure is actually used to ensure that the product performs exactly as it is intended to. The
testing phase aims to accomplish the following objectives: - To validate the project's quality.
To identify and fix any leftover mistakes from earlier steps.
To confirm that the software is a viable fix for the original issue.
To guarantee the system's operational reliability.
Some of the important testing methodologies are: Unit Testing, Integration Testing and System
Testing.
Unit Testing - Unit testing is the first level of testing and is often performed by the developers
themselves.
Integration Testing - After each unit is thoroughly tested, it is integrated with other units to create
modules or components that are designed to perform specific tasks or activities.
System Testing - System testing is a black box testing method used to evaluate the completed and
integrated system, as a whole, to ensure it meets specified requirements.

28
Chapter 8:
Conclusion And Future Scope
8.1 Conclusion
In this project, we have made the movie recommender system which recommends movies based on
the content that is the most similar to what the user searches on the site. We have used cosine
similarity to find out which top 5 movies would be the closest to what the user searches. This system
tries to save up the time for the users who want to watch a movie similar to watch what they had
watched before. We have used movie datasets from Kaggle.com which contained information like
genre, cast, movie title, keywords in the movie, language and any more to preprocess the data and
filter and gather all the information that would to be required to find out all the relevant data for
content-based filtering.
8.2 Future scope
In the proposed approach, we have used content based filtering, further we can move onto the hybrid
filtering which would contain both content based and collaborative based filtering in the model. We
can also put up and options for register/login so that the information of the users would be stored in
the database and can be further used for collaborative filtering.

29
BIBLIOGRAPHIES
https://developers.google.com/
https://www.geeksforgeeks.org/
https://www.tutorialspoint.com/
https://www.askpython.com/
https://www.javatpoint.com/
https://stackoverflow.com/
https://stackexchange.com/

final report.pdf

More Related Content

What's hot (20)

Similar to final report.pdf (20)

Recently uploaded (20)

final report.pdf