Prediction and
Recommendation Of Movies To
Users
Shreyansh Kumar Jayesh Talreja Shashank Kaushik Sharma
(RA2011033010008) (RA2011033010021) (RA2011033010018)
Content
• Introduction
• Problem statement
• Literature Survey
• Limitations
• Objectives
• Architecture/block diagram
• Modules with explanations
Contributions
• RA2011033010018 - Introduction, Problem statement,
Modules with explanations
• RA2011033010021 - Limitations, Objectives
• RA2011033010008 - Literature Survey,
Architecture/block diagram,.
Introduction
• This project aims to build an AI-based movie
recommendation system that provides personalized
recommendations to users based on their viewing
history and preferences. The system will use machine
learning algorithms to analyze vast amounts of data,
including movie ratings, genres, actors, directors, and
even user reviews and comments, to predict what users
are likely to watch next. The goal is to enhance the user's
viewing experience by saving them time and effort in
searching for movies and introducing them to new
movies that they may enjoy.
Problem Statement
In today's digital age, there are a plethora of movie options available for
users to choose from, making it difficult to decide what to watch. With so
many options, users often spend a lot of time scrolling through various movie
platforms, trying to find something that interests them. This can lead to
frustration and even decision fatigue, causing them to give up and not watch
anything at all.
To solve this problem, we aim to build an Artificial Intelligence system that
predicts and recommends movies to users based on their preferences. The
system will analyze the user's viewing history, movie ratings, and other
factors like genre, actors, and director preferences to provide personalized
recommendations.
Literature Survey
S.NO Paper Name and Year Inferences
1 "A Hybrid Collaborative Filtering Algorithm for Movie Recommendation The paper proposes a hybrid collaborative filtering
based on User Preferences and Item Attributes" by IEEE Access - 2021 algorithm that combines both user preference and item
attributes for movie recommendation. The proposed
algorithm outperforms existing collaborative filtering
algorithms in terms of prediction accuracy
2 "Deep Learning for Recommender Systems: A Survey and Future The paper presents a survey of deep learning-based
Directions“ by IEEE Transactions on Neural Networks and Learning recommender systems, including movie
Systems - 2020 recommendation. The survey covers various deep
learning architectures and techniques, such as neural
collaborative filtering, deep matrix factorization, and
deep reinforcement learning. The paper also discusses
the challenges and opportunities in the field of deep
learning-based movie recommendation.
3 "A Hybrid Collaborative Filtering and Deep Learning Approach for The paper proposes a hybrid approach that combines
Movie Recommendation“ by International Journal of Machine Learning collaborative filtering and deep learning techniques for
and Cybernetics - 2022 movie recommendation. The hybrid approach
outperforms both traditional collaborative filtering and
deep learning-based approaches in terms of
prediction accuracy. The paper also discusses the
challenges and opportunities in the field of hybrid
movie recommendation.
Literature Survey
S.No Paper Name and Year Inferences
4 “Towards privacy in a context-aware social network based recommendation system” Focus on protecting data and request for
by P. W. Yau and A. Tomlinson-2021 data, at the point of data collection. This
paper outlines a hierarchical privacy
architecture, to provide anonymity, unlink
ability, unobservability and pseudonymity to
IK users. Users are grouped according to
`proportional distance reservation', which
indicates how likely users are willing to share
private information. The protection of private
information is stronger when queries are
made by `distant' users, and weaker for fellow
group members.
5 “Recommender systems in ecommerce” by J. Ben Schafer, Joseph Konstan, John Riedl The ideas of new applications in the field of
GroupLens Research Project Department of Computer Science and Engineering recommendation systems in e-commerce
University of Minnesota Minneapolis-2020 sites. we create a taxonomy of recommender
systems, including the interfaces they present
to customers, the technologies used to create
the recommendations, and the inputs they
need from customers
6 Recommender Systems: An overview of different approaches to recommendations by Many popular Ecommerce sites widely use
Kunal Shah, Akshaykumar Salunke, Saurabh Dongare, Kisandas Antala SIT, Lonavala RSs to recommend news, music, research
India-2022 articles, books, and product items.
Recommendation systems use personal,
implicit and local information from the
Internet. This paper attempts to describe
various limitations of recommendation
Limitations
1.Cold-start problem: One of the primary challenges of
movie recommendation systems is the cold-start problem,
which occurs when a new user or a new movie is introduced
into the system. The system may not have enough data to
provide personalized recommendations, which may result in
inaccurate recommendations.
2.Limited data availability: Another limitation of movie
recommendation systems is the availability of limited data.
Some movies may not have enough ratings or reviews,
making it challenging for the system to provide accurate
recommendations.
Limitations Contd.
3.Lack of diversity: Movie recommendation systems may
suggest similar types of movies to users, resulting in a lack of
diversity in their viewing experience.
4.Overreliance on past behavior: Movie recommendation
systems are based on past behavior, such as viewing history
and ratings. However, users' preferences may change over
time, and their current preferences may not be reflected in
their past behavior.
Limitations Contd.
5.Bias: Recommendation systems may be biased towards
certain movies, genres, or actors, resulting in unfair
recommendations.
6.Privacy concerns: Movie recommendation systems require
access to users' personal data, such as viewing history and
ratings, which may raise privacy concerns among users.
Objectives
1.Provide personalized recommendations: The primary
objective of a movie recommendation system is to provide
personalized recommendations to users based on their
viewing history and preferences.
2.Enhance user experience: The system should enhance the
user's viewing experience by saving them time and effort in
searching for movies and introducing them to new movies
that they may enjoy.
Objectives Contd.
3.Increase engagement: The system should increase user
engagement by providing relevant and accurate
recommendations, encouraging them to continue using the
service.
4.Ensure diversity: The system should ensure diversity in
recommendations by suggesting different types of movies to
users, avoiding over-reliance on a particular genre or actor.
Architecture Diagram
Modules
1.Data collection module: This module is responsible for
collecting data from various sources, such as movie databases and
user ratings, to build a dataset for the recommendation system.
2.Data preprocessing module: This module is responsible for
cleaning and processing the collected data, including removing
duplicates, handling missing data, and transforming the data into
a format suitable for machine learning algorithms.
3.Machine learning module: This module uses various machine
learning algorithms, such as collaborative filtering, content-based
filtering, and matrix factorization, to generate recommendations
based on the user's viewing history and preferences.
Modules Contd.
4.Recommendation generation module: This module generates a
list of recommended movies based on the output of the machine
learning module, taking into account factors such as movie
ratings, genre, and popularity.
5.Recommendation filtering module: This module filters the
generated recommendations based on various criteria, such as
user age, language, and location, to provide more personalized
recommendations.
6.Recommendation ranking module: This module ranks the
filtered recommendations based on their relevance and
importance to the user, taking into account factors such as
viewing history and ratings.
THANK YOU…
Shreyansh Kumar Jayesh Talreja Shashank Kaushik Sharma
(RA2011033010008) (RA2011033010021) (RA2011033010018)
