Movie Recommendation System

A Project Work Synopsis

Submitted in the partial fulfillment for the award of the degree of

BACHELOR OF ENGINEERING
IN
COMPUTER SCIENCE WITH SPECIALIZATION IN
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING

Submitted by:

Ankita Bhau 20BCS4637

Daksh Pratap Singh 20BCS4605
Dhruv Aggarwal 20BCS4617
Anuj Jindal 20BCS4616
Ronak choudhary 20BCS4635

Under the Supervision of:

1
 CHANDIGARH UNIVERSITY, GHARUAN, MOHALI - 140413,
PUNJAB
September, 2022
Table of Contents

Title Page i
Abstract ii
1. Introduction
1.1 Problem Definition
1.2 Project Overview
1.3 Hardware Specification
1.4 Software Specification
2. Literature Survey
2.1 Existing System
2.2 Proposed System
2.3 Literature Review Summary
3. Problem Formulation
4. Research Objective

2
5. Methodologies

6. Conclusion

7. Reference

3
1. INTRODUCTION
Introduction:
Movie recommendation systems are used to suggest movies to users
based on their preferences, watching history, and other factors. These
systems have become more popular in recent years due to the
increase in online streaming services such as Netflix, Amazon Prime
Video, and Hulu. The aim of this project is to build a movie
recommendation system using machine learning algorithms.

Objective: The objective of this project is to build a movie

recommendation system that suggests movies to users based on their
preferences and watching history. The system should be able to
provide accurate and relevant recommendations to users.

Methodology: The project will use the Movie Lens dataset, which is
a publicly available dataset that contains 100,000 movie ratings from
943 users. We will use Python programming language and Jupyter
Notebook for data cleaning, data exploration, and data analysis. The
project will use the following machine learning algorithms for
building the recommendation system:

Content-based recommendation system: In this type of

recommendation system, we will use the movie's features such as
genre, director, and actors to recommend similar movies to the user.
 We will use the cosine similarity algorithm to calculate the similarity
between movies based on their features.

Collaborative filtering recommendation system: In this type of

recommendation system, we will use the user's past behavior such as
movie ratings and watched movies to recommend movies. We will
use the K-nearest neighbor algorithm to find the most similar users
and then recommend movies based on their ratings.

Hybrid recommendation system: In this type of recommendation

system, we will combine both content-based and collaborative
filtering approaches to provide better recommendations. We will
use a weighted average method to combine both approaches.

2. LITERATURE SURVEY
A movie recommendation system based on collaborative filtering
approach collaborative filtering take the data from all the users and
based on that generates recommendation . This combine both
collaborative and content based method . There were also made an
analysis of both the traditional recommendation techniques. As
both of these techniques have certain setbacks, he proposed
5
 another system which is a combination of Bayesian network and
collaborative technique. There is a proposed clustering as an
approach to handle there commendations. Two methods for
clustering were analyzed.: .2 Centroid-based solution and
memory-based methods. The result was that accurate
recommendations were generated. Someone proposed Movie
Recommender, a system that uses the user’s history in order to
generator commendations . We have analyzed various techniques
used for recommendations, collaborative, hybrid and content-
based recommendations. Also, it describes the pros and cons of
these approaches. We have also proposed an inductive learning
algorithm. Here a tree had been built which shows the user
recommendation.

3. PROBLEM FORMULATION

collaborative and content based method . There were also made an

analysis of both the traditional recommendation techniques. As both of
these techniques have certain setbacks, he proposed another system
which is a combination of Bayesian network and collaborative technique.
There is a proposed clustering as an approach to handle there
commendations. Two methods for clustering were analyzed.: .2 Centroid-
based solution and memory-based methods. The result was that accurate
recommendations were generated. Someone proposed Movie
Recommender, a system that uses the user’s history in order to generator
6
commendations . We have analyzed various techniques used for
recommendations, collaborative, hybrid and content-based
recommendations. Also, it describes the pros and cons of these
approaches. We have also proposed an inductive learning algorithm. Here
a tree had been built which shows the user recommendation. Collect and
preprocess data: Collect and preprocess data on user preferences, movie
information, and other relevant features. This could involve gathering
data from various sources such as user ratings, reviews, and metadata.
Develop a recommendation algorithm: Develop a recommendation
algorithm that can analyze user data and movie data to make personalized
movie recommendations. This algorithm could be based on collaborative
filtering, content-based filtering, or a hybrid of the two. Evaluate the
system: Evaluate the effectiveness of the recommendation system by
measuring metrics such as accuracy, precision, and recall, and making
adjustments as needed. Overall, the problem definition of a movie
recommendation system involves designing a system that can effectively
analyze user preferences and movie data to provide personalized and
accurate movie recommendations

7
4. OBJECTIVES

The objective of this project is to build a movie

recommendation system that suggests movies to users based on
their preferences and watching history. The system should be
able to provide accurate and relevant recommendations to users.
The primary objective of a movie recommendation system is to
provide personalized movie suggestions to users based on their

8
interests and viewing history. This helps users to discover new
movies that they are likely to enjoy, and provides a better
overall user experience for movie streaming services.
Increasing user engagement: By providing personalized movie
recommendations, users are more likely to stay engaged with a
movie streaming service and continue using it over time

9
5. METHODOLOGY

The dataset used in this study is the MovieLens dataset. It is a

publicly available dataset that contains 100,000 movie ratings
from 943 users. We used Python programming language and
Jupyter Notebook for data cleaning, data exploration, and data
analysis. We have used the following machine learning algorithms
for building our recommendation system. 1. Content-based
recommendation system: In this type of recommendation system,
we use the movie's features such as genre, director, and actors to
recommend similar movies to the user. We have used the cosine
similarity algorithm to calculate the similarity between movies
based on their features. 2. Collaborative filtering recommendation
system: In this type of recommendation system, we use the user's
past behavior such as movie ratings and watched movies to
recommend movies. We have used the K nearest neighbor
algorithm to find the most similar users and then recommend
movies based on their ratings. 3. Hybrid recommendation system:
In this type of recommendation system, we combine both
contentbased and collaborative filtering approaches to provide
10
better recommendations. We have used a weighted average
method to combine both approaches

11
7.CONCLUSION
In conclusion, movie recommendation systems using machine
learning have become increasingly popular due to their ability to
provide personalized recommendations to users. These systems
utilize various machine learning algorithms such as collaborative
filtering, content-based filtering, and hybrid filtering to analyze user
data and provide recommendations. The effectiveness of the system
largely depends on the quality of data used for training the algorithms
and the choice of the algorithm used. Furthermore, such systems can
be improved by incorporating other factors such as contextual
information, user feedback, and social network data. Overall, the use
of machine learning in movie recommendation systems has
revolutionized the movie industry and has made it easier for users to
discover new movies and TV shows that match their preferences.

12
REFERENCES

[1] "Recommender Systems Handbook" edited by Francesco Ricci,

Lior Rokach, Bracha Shapira, and Paul B. Kantor.J. Clerk Maxwell,
A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford:
Clarendon, 1892, pp.68–73. [2] "A Survey of Recommendation
System Research" by Jie Lu, Guangquan Zhang, and Yuanyuan Yan.
[3] "An Empirical Study of Collaborative Filtering-Based
Recommendation Algorithms" by Xiaoyuan Su and Taghi M.
Khoshgoftaar. [4] "Content-based and Collaborative Filtering
Recommender Systems: A Unified Framework" by Yi Fang and Luo
Si. [5] "A Hybrid Collaborative Filtering Recommender System using
Deep Learning and Recommender Systems Algorithms" by Islem
Rekik, Mohamed K. Ghazy, and Jemal Abawajy. [6] "Machine
Learning Techniques for Recommender Systems" by Robin Burke.

13