A Project Report

on
HYBRID MOVIE RECOMMENDATION SYSTEM
Submitted in partial fulfillment of the
requirement for the award of the degree of

Bachelor of Technology in Computer Science &

Engineering

Under The Supervision of

Dr.Amit Kumar Goel
Professor
Department of Computer Science and Engineering

Submitted By:
Abhinav Pengoria-18SCSE1010126
Abhishek Kumar-18SCSE1010334

SCHOOL OF COMPUTING SCIENCE AND ENGINEERING

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING /
DEPARTMENT OF COMPUTERAPPLICATION
GALGOTIAS UNIVERSITY, GREATER NOIDA
INDIA
DECEMBER - 2021
 SCHOOL OF COMPUTING SCIENCE AND
ENGINEERING
GALGOTIAS UNIVERSITY, GREATER NOIDA

CANDIDATE’S DECLARATION
I/We hereby certify that the work which is being presented in the project, entitled “HYBRID

MOVIE RECOMMENDATION SYSTEM” in partial fulfillment of the requirements for the

award of the BACHELOR OF TECHNOLOGY IN COMPUTER SCIENCE AND

ENGINEERING submitted in the School of Computing Science and Engineering of

Galgotias University, Greater Noida, is an original work carried out during the period of SEP-

2021 to DEC-2021, under the supervision of Dr.Amit Kumar Goel, Professor, Department of

Computer Science and Engineering of School of Computing Science and Engineering,

Galgotias University, Greater Noida

The matter presented in the project has not been submitted by me/us for the award of any

other degree of this or any other places.

Abhinav Pengoria - 18SCSE1010126

Abhishek Kumar - 18SCSE1010334

This is to certify that the above statement made by the candidates is correct to the best of my

knowledge.

Dr.Amit Kumar Goel

Professor
 CERTIFICATE

The Final Thesis/Project/ Dissertation Viva-Voce examination of Abhinav Pengoria-

18SCSE1010126, Abhishek Kumar - 18SCSE1010334 has been held on _________________

and his/her work is recommended for the award of BACHELOR OF TECHNOLOGY IN

COMPUTER SCIENCE AND ENGINEERING.

Signature of Examiner(s) Signature of Supervisor(s)

Signature of Project Coordinator Signature of Dean

Date: December, 2021

Place: Greater Noida

 TABLE OF CONTENTS

CHAPTER TITLE PAGE NO

Candidates Declaration 2
Certificate 3
Abstract 5
1 Introduction 6
1.1 Objective 7
1.2 Problem Statement 8
Literature Survey
2.1 Background
2.2 Existing Product And System
2 9
2.3 System Study
2.4 Hybrid Recommendation And Approach
2.5 Survey of Technology
Requirements and Analysis
3 18
3.1 Software and Hardware Requirements
Conceptual Models
4.1 DFD
4.2 ER Diagram
4.3 Class Diagram
4.4 State Diagram
4 20
4.5 Architecture Diagram
4.6 Sequence Diagram
4.7 Use Case Diagram
4.8 Flow Chart
4.9 Activity Diagram
Design
5 35
5.1 System Design
Implementation and Testing
6 36
6.1 Python Code and Output
7 Conclusion
47
8 References 48
 ABSTRACT

These days, recommendation systems have made discovering the things

simple that we need. Movie recommendation systems target helping movies

devotees by recommending what movies to observe without having to go

through the long process of choosing from a large set of movies that go up to

thousands and millions that is time-consuming and confusing. In this project,

our point is to lessen human exertion by proposing motion pictures dependent

on the client's advantages. to handle such problems, we introduced a model

combining both content-based and collaborative approaches. It will give

logically express results contrasted with various frameworks that depend on a

content-based approach. Content-based proposal frameworks are compelled

to individuals, these frameworks don't endorse things out of the container,

along these lines restricting your decision to investigate more. In all what we

are trying to say is that we have focused on a framework that is able to settle

these issues.
 INTRODUCTION

A proposal framework is a sort of data sifting framework which endeavors to

anticipate the inclinations of a client, and make recommends dependent on these
inclinations. There are a wide assortment of utilization for suggestion frameworks.
These have become progressively well known in the course of the most recent
couple of years and are currently used in most internet based stages that we use.
The substance of such stages differs from films, music, books and recordings, to
companions and stories via online media stages, to items on web based business
sites, to individuals on expert and dating sites, to indexed lists returned on Google.
Frequently, these frameworks can gather data about a clients decisions, and can
utilize this data to improve their ideas later on.For instance, Facebook can screen
your cooperation with different stories on your feed to realize what sorts of stories
appeal to you. Here and there, the recommender frameworks can make upgrades
dependent on the exercises of an enormous number of individuals. For instance, if
Amazon sees that countless clients who purchase the most recent Apple Macbook
additionally purchase a USB-C-to USB Adapter, they can suggest the Adapter to
another client who has recently added a Macbook to his truck. Because of the
advances in recommender frameworks, clients continually anticipate great
proposals. They have a low edge for administrations that can't make suitable ideas.
On the off chance that a music streaming application isn't ready to anticipate and
play music that the client likes, then, at that point, the client will basically quit
utilizing it.This has prompted a high accentuation by tech organizations on further
developing their proposal frameworks. Be that as it may, the issue is surprisingly
complicated. Each client has various inclinations also, likes. Also, even the flavor
of a solitary client can fluctuate contingent upon an enormous number of factors,
like state of mind, season, or sort of action the client is doing. For instance, the sort
of music one might want to hear while practicing varies significantly from the kind
of music he'd pay attention to when preparing supper. Another issue that
suggestion frameworks need to tackle is the investigation versus abuse issue.They
should investigate new areas to find more concerning the client, while as yet
capitalizing on what is as of now thought about of the client. Three fundamental
methodologies are utilized for our recommender frameworks. One is Demographic
Filtering i.e They submit summed up proposals to each client, in light of film
ubiquity and additionally 7 type. The System prescribes similar motion pictures to
clients with comparative segment highlights. Since every client is unique , this
methodology is viewed as excessively straightforward. The fundamental thought
behind this framework is that motion pictures that are more well known and widely
praised will have a higher likelihood of being enjoyed by the normal crowd.
Second is content-based sifting, where we attempt to profile the clients intrigues
utilizing data gathered, and suggest things in view of that profile. The other is
communicant sifting, where we attempt to bunch comparable clients together and
use data about the gathering to make suggestions to the client.

1.1 Objectives

Hybrid Movies Recommendation System goal is to recommended movies by

merging two recommendation system i.e, content based and collaborative filtering
and create a system which possesses both system properties.

The main goal of the our system is:

I. To recommend movies.
II. To recommend movies based on user history i.e, the next movies recommended
based on the number of times the user watches a certain genre of movie.
III. To recommend movies based on overall rating i.e, movies which are famous
and these movies can have different genre also.

1.2 Problem Statement

Providing related content out of relevant and irrelevant collection of items to users
of online service providers.

Hybrid movies recommendation system aims to recommend movies to users based

on user-movie (item) ratings.

Given a set of users with their previous ratings for a set of movies, can we predict
the rating they will assign to a movie they have not previously rated?
 LITERATURE SURVEY

With regards to a survey of the writing, a suggestion framework utilizing a

substance based collective and mixture approach by a past specialist is an alternate
way to deal with the improvement of proposal based motors. In 2007 a web based
and information based knowledge film suggestion framework has been offered
utilizing the crossover sifting technique . In 2017, a film proposal framework
upheld style and rating coefficient of connection reason by the creators. In 2013 a
Bayesian organization and trust model based film suggestion motor have been
prescribed to anticipate evaluations for clients and things, essentially from datasets
to suggest clients their decision as well as the other way around.In 2018, the
creators constructed a suggestion motor by investigating the evaluations data set
gathered from Kaggle to suggest films for a client chosen from Python. In 2018
film suggestion motors give a cycle to assist clients classify clients with
comparable k-mean cuckoo esteems and support learning based recommender
frameworks, which are utilizing bicycling procedures . Starting exploration mostly
focused on the substance of the suggestion framework that inspected the provisions
of the item to finish the proposal task. Tests checked that their methodologies were
more flexible and exact. Bayesian networks are utilized for model-put together
inclinations based with respect to their specific situation.At the point when
customers embrace new conduct, it is hard for community sifting to respond in a
flash. Accordingly, the two analysts and professionals want to adjust community
sifting strategy and content-based technique to address the issue. Ternary executed
Unplugged Learning of Machine Learning to inspect the extremity of machine
reflectivity.
2.1 Background
Over the past decade, a large number of recommendation systems for a variety of
domains have been developed and are in use. These recommendation systems use a
variety of methods such as content based approach, collaborative approach,
knowledge based approach, utility based approach, hybrid approach, etc. Most of
the online recommendation systems for a variety of items use ratings from
previous users to make recommendations to current users with similar interests.
One such system was designed by Jung, Harris, Webster and Her locker (2004) for
improving search results. The system encourages users to enter longer and more
informative search queries, and collects ratings from users as to whether search
results meet their information need or not. These ratings are then used to make
recommendations to later users with similar needs.

2.2 Existing product and system

Current Social Networking World Internet social networking sites, which began in
1995 with Classmates.com, have surged in popularity and use through word-of-
mouth advertising. Since then, a wide range of virtual communities have formed
serving different purposes and targeting varying niche audiences:recommendation
system and haven't taken advantage of social-networking communities or crowd
wisdom. Some websites, such as Blockbuster, do provide individualized
recommendations based on a user's ratings but do not include any social
networking component. Yahoo! Movies goes further and uses personal ratings to
suggest movies currently playing in theatre, on TV, and out on DVD. It also draws
upon its vast user base to give lists of similar movie fans, their ratings, and reviews.
Other movie sites, like Flixster, take a different approach. Flixster forms web based
communities around movies and suggests movies to watch based on what your
friends have rated.
2.3 Movie Recommendation System by K-Means Clustering AND K-Nearest
Neighbour.
A recommendation system collect data about the user’s preferences either
implicitly or explicitly on different items like movies. An implicit acquisition in
the development of movie recommendation system uses the user’s behaviour while
watching the movies. On the other hand, a explicit acquisition in the development
of movie recommendation system uses the user’s previous ratings or history. The
other supporting technique that are used in the development of recommendation
system is clustering. Clustering is a process to group a set of objects in such a way
that objects in the same clusters are more similar to each other than to those in
other clusters. K-Means Clustering along with K-Nearest Neighbour is
implemented on the movie lens dataset in order to obtain the best-optimized result.
In existing technique, the data is scattered which results in a high number of
clusters while in the proposed technique data is gathered and results in a low
number of clusters. The process of recommendation of a movie is optimized in the
proposed scheme. The proposed recommender system predicts the user’s
preference of a movie on the basis of different parameters. The recommender
system works on the concept that people are having common preference or choice.
These users will influence on each other’s opinions. This process optimizes the
process and having lower RMSE.

2.4 Movie Recommendation System Using Collaborative Filtering:

Collaborative filtering systems analyse the user's behaviour and preferences and
predict what they would like based on similarity with other users. There are two
kinds of collaborative filtering systems; user-based recommender and item-based
recommender.
A. Use-based filtering: User-based preferences are very common in the field of
designing personalized systems. This approach is based on the user's likings. The
process starts with users giving ratings (1-5) to some movies. These ratings can be
implicit or explicit. Explicit ratings are when the user explicitly rates the item on
some scale or indicates a thumbs-up/thumbs-down to the item. Often explicit
ratings are hard to gather as not every user is much interested in providing
feedback's. In these scenarios, we gather implicit ratings based on their behaviour.
For instance, if a user buys a product more than once, it indicates a positive
preference. In context to movie systems, we can imply that if a user watches the
entire movie, he/she has some like ability to it. Note that there are no clear rules in
determining implicit ratings. Next, for each user, we first find some defined
number of nearest neighbors. We calculate correlation between users' ratings using
Pearson Correlation algorithm. The assumption that if two users' ratings are highly
correlated, then these two users must enjoy similar items and products is used to
recommend items to users.

B. Item-based filtering: Unlike the user-based filtering method, item based

focuses on the similarity between the item’s users like instead of the users
themselves. The most similar items are computed ahead of time. Then for
recommendation, the items that are most similar to the target item are
recommended to the user.
2.5 System Study

Feasibility Study
The feasibility of the project is analyzed in this phase and business proposal is put
forth with a very general plan for the project and some cost estimates. During
system analysis the feasibility study of the proposed system is to be carried out.
This is to ensure that the proposed system is not a burden to the company. For
feasibility analysis, some understanding of the major requirements for the system
is essential.

Three key considerations involved in the feasibility analysis are:

Economical Feasibility
Technical Feasibility
Social Feasibility

Economical Feasibility:

This study is carried out to check the economic impact that the system will have on
the organization. The amount of fund that the company can pour into the research
and development the system is limited. The expenditures must be justified. Thus
the developed system as well within the budget and this was achieved because
most of the technologies used are freely available. Only the customized products
had to be purchased.
Technical Feasibility:

This study is carried out to check the technical feasibility, that is, the technical
requirements of the system. Any system developed must not have a high demand
on the available technical resources. This will lead to high demands on the
available technical resources. This will lead to high demands being placed on the
client. The developed system must have a modest requirement, as only minimal or
null changes are required for implementing this system.

Social Feasibility:

The aspect of study is to check the level of acceptance of the system by the user.
This includes the process of training the user to use the system efficiently. The user
must not feel threatened by the system, instead must accept it as a necessity. The
level of acceptance by the users solely depends on the methods that are employed
to educate the user about the system and to make him familiar with it. His level of
confidence must be raised so that he is also able to make some constructive
criticism, which is welcomed, as he is the final user of the system.

2.6 Hybrid Recommendation And Approach

One common occurrence in RSS research is the demand to combine

recommendation techniques to achieve peak performance. All of the known
recommendation techniques have advantages and disadvantages, and many
researchers have chosen to combine techniques in different ways in order to
leverage their advantages. This session surveys the different hybrid
recommendation approaches.
Hybrid systems combine two or more techniques in order to gain better
performance with fewer limitations of each approach. Many hybrid systems have
been applied to travel and tourism applications. For instance F. Ricci et al.
illustrate a travel planning.recommender system that is case-based, hence is
knowledge-based, but also Collaborative-based since it recommends travel services
that have been evaluated positively by others.

Fab is a recommendation system designed to help users explore the enormous

amount of information available on the internet. This hybrid system combines the
Content-based and Collaborative methods of recommendation in a way that
exploits the advantages of the two approaches while avoiding their shortcomings.
Fab's hybrid structure allows for automatic recognition of emergent issues relevant
to various groups of users. It also enables two scaling problems pertaining to the
rising number of users and documents, to be addressed.

One major tactic for improving recommendation is to combine Collaborative

filtering with Content-based recommenders. We can illustrate the benefits of such
hybrid systems with a simple example; suppose one user has rated the NBA page
from CBSSports.com favorably, while another has rated the NBA page from
CNNSL.com favorably, pure Collaborative filtering would find no correlation
between the two users. However, Content analysis can show that the two items are
in fact quite similar, thus indicating.
2.7 Survey of Technologies

Hybrid Movies Recommendation System goal is to recommended movies by

merging two recommendation system i.e, content based and collaborative filtering
and create a system which possesses both system properties.

PYTHON :
 Python is a popular programming language.
 Python is an interpreted high-level general-purpose programming
language.
 Python can be used on a server to create web applications.
 Python can be used alongside software to create workflows.
 Python can connect to database systems. It can also read and modify
files.
 Python can be used to handle big data and perform complex

mathematics.
 Python can be used for rapid prototyping, or for production-ready

software development.
 Python works on different platforms (Windows, Mac, Linux,
Raspberry Pi, etc).
 Python has a simple syntax similar to the English language.
 Python has syntax that allows developers to write programs with
fewer lines than some other programming languages.
 Python runs on an interpreter system, meaning that code can be
executed as soon as it is written. This means that prototyping can be
very quick.
 Python can be treated in a procedural way, an object-oriented way or a
functional way.
 Python was designed for readability, and has some similarities to the
English language with influence from mathematics.
 Python uses new lines to complete a command, as opposed to other
programming languages which often use semicolons or parentheses.
 Python relies on indentation, using whitespace, to define scope; such
as the scope of loops, functions and classes. Other programming
languages often use curly-brackets for this purpose.
 Python Comments can be used to explain Python code.
 Python Comments can be used to make the code more readable.
 Python Comments can be used to prevent execution when testing code.
 It supports functional and structured programming methods as well as
OOP.
 It can be used as a scripting language or can be compiled to byte-code
for building large applications.
 It provides very high-level dynamic data types and supports dynamic
type checking.
 It supports automatic garbage collection.
 It can be easily integrated with C, C++, COM, ActiveX, CORBA, and
Java.
 Python supports multiple programming pattern, including object-
oriented, imperative, and functional or procedural programming styles.
 Python is not intended to work in a particular area, such as web
programming. That is why it is known as multipurpose programming
language because it can be used with web, enterprise, 3D CAD, etc.
 REQUIREMENTS AND ANALYSIS

Problem Definition
This paper is based on recommendation system that recommends different things
to users. This system will recommend movies to users. This system will provide
more precise results as compared to the existing systems. The existing system
works on individual users' rating. This may be sometime useless for the users who
have different taste from the recommendations shown by the system as every user
may have different tastes. This system calculates the similarities between different
users and then recommend movie to them as per the ratings given by the different
users of similar tastes. This will provide a precise recommendation to the user.

Providing related content out of relevant and irrelevant collection of items to users
of online service providers.

Hybrid movies recommendation system aims to recommend movies to users based

on user-movie (item) ratings.

Given a set of users with their previous ratings for a set of movies, can we predict
the rating they will assign to a movie they have not previously rated?

Requirement Specification

Hybrid Movies Recommendation System provides the Customers with better and
more efficient means of movies recommendation system and from all over the
world. Technologies such as python.
  Python is a popular programming language.
 Python is an interpreted high-level general-purpose programming
language.
 Python can be used on a server to create web applications.
 Python can be used alongside software to create workflows.
 Python can connect to database systems. It can also read and modify
files.
 Python can be used to handle big data and perform complex
mathematics.

SOFTWARE AND HARDWARE REQUIREMENTS

Hardware Used

1. Intel Core 2 Quad Q9550,E0 revision

2. 4 GB PC2-6400 800Mhz RAM
3. 500 GB Hard disk drive

Software Requirements

1. Windows 7 Ultimate
2. IE8/Firefox/Safari

Preliminary Product Description

We indulged ourselves into a lot of research before we started the actual work on
the ― “HYBRID MOVIES RECOMMENDATION SYSTEM” application. We
Studied about the different kinds of movies recommendation system such as
content based and collaborative filtering that were needed to build our application.
 CONCEPTUAL MODELS

DATA FLOW DIAGRAM

1-Data Flow

An arrow represents data flow; it represents the path over which data travels
in the system? A data flow can move between processes, flow into or out of
data stores, to and from external entities.

2-Bubbles (Process)

A circle or bubble represents that transforms data from once form to another
by performing some tasks with the data.

3-Data store

A data store is a place where data is held temporarily from one transaction to
the next or is stored permanently.

4-Entity

External Entity symbol represents sources of data to the system or

destinations of data from the system.
Fig:1 Data Flow Diagram
E-R DIAGRAM
1-Entity
Entity has a set of attribute whose value is uniquely, identify the entity or
distinguish the entity from the other thing or entity in the world.

2-Attribute
Are used to define an entity that is the property that describe an entity. That
is the properly that describe an entity.

3-Relationship
Is association among different/several,entities. It connect to one or more
entities.

4-Derived
Attribute Any attribute which is derived from the relationship is called
derived attribute.

5-Cardinality
Carnality refers to the multiplicity of the entities. How many entity are
actually engaged in the relationship.

Types of cardinality:-
1. Many to 1
2. 1 to 1
3. 1 to Many
4. Many to Many
Fig:2 ER Diagram
CLASS DIAGRAM

Class diagram in the Unified Modeling Language (UML) is a type of static

structure diagram that describes the structure of a system by showing the system's
classes, their attributes, operations (or methods), and the relationships among
objects.

 The above class diagram describes the classes, attributes and methods of movie
recommendation system.

 Input movie data: It is class which takes the data of the movie details.

 A priori algorithm: This class will do analyses based on the given data and
suggests movie.

 Movie selection: This class helps in selecting movie based on the genre and the
movie ratings.

 Movie suggestion: This class suggests the movie to user based on the
frequently watched movie(genre).
Fig:3 Class Diagram
STATE DIAGRAM

A state diagram is a diagram used in computer science to describe the behavior of a

system considering all the possible states of an object when an event occurs. State
diagrams graphically represent finite state machines. They are only used to
understand object behavior throughout the whole system.

 In the above diagram it describes the behavior of movie recommendation

system.

 When the data of movie is given it checks for the similar genre by using
recommendation algorithm and suggests the movie to user.

 Suggestion is based on the movie ratings, genre, language and frequently

watched movies.

 If the previously watched movie's rating is three, then the suggested movie's
rating should be equal or greater than three.
Fig:4 State Diagram
ARCHITECTURE DIAGRAM

An architecture diagram is a graphical representation of a set of concepts, that are

part of an architecture, including their principles, elements and components. ... An
Example Architecture Diagram of an Enterprise Architecture to create a Modern
Smart and Green Company, using various concepts and principles.

Fig:5 Architecture Diagram

SEQUENCE DIAGRAM

A sequence diagram simply depicts interaction between objects in a sequential

order i.e. the order in which these interactions take place. We can also use the
terms event diagrams or event scenarios to refer to a sequence diagram. Sequence
diagrams describe how and in what order the objects in a system function.

 Once a movie is selected by the user the server gets the details of his previously
watched movies.

 The information is stored and if we want to see the information again we can
just check for the user history using the user id.

 For further the recommendation can be shared with friends on different

platforms.

 The generation of recommendations goes on in loop until the user selects one
for his watch.
Fig:6 Sequence Diagram
USE CASE DIAGRAM

A use case shows a set of use cases, actors and their relationship. The use case
diagram make system and classes approachable by presenting an outside view of
how the elements may be used in context.

Fig:7 Use Case Diagram

FLOW CHART

A flowchart is a diagram that depicts a process, system or computer algorithm.

They are widely used in multiple fields to document, study, plan, improve and
communicate often complex processes in clear, easy-to-understand diagrams.
Flowcharts, sometimes spelled as flow charts, use rectangles, ovals, diamonds and
potentially numerous other shapes to define the type of step, along with connecting
arrows to define flow and sequence. They can range from simple, hand-drawn
charts to comprehensive computer-drawn diagrams depicting multiple steps and
routes.

Fig:8 Flow Chart

ACTIVITY DIAGRAM

Activity diagram is defined as a UML diagram that focuses on the execution and
flow of the behavior of a system instead of implementation. It is also called object-
oriented flowchart. Activity diagrams consist of activities that are made up of
actions which apply to behavioral modeling technology.

 Firstly, have to enter the user credentials.

 If a new user has to register.
 Then select the applicable genre and the movies are recommended.

 Identify candidate use cases, through the examination of business workflows.

 Identify pre- and post-conditions (the context) for use cases.

 Model workflows between/within use cases.

 Model complex workflows in operations on objects.

 Model in detail complex activities in a high level activity Diagram

 For this the system uses the A priori algorithm, and thus the process continues
and always a new recommendation list is generated.
Fig:9 Activity Diagram
 SYSTEM DESIGN
For each different individual use different list of movies are
recommended ,as user login or enters the user id based on two different
approaches used in the project each will recommend the set of movies to the
particular user by combining the both the set of movie based on the user the
hybrid model will recommend the single list of movie to the user.
 IMPLEMENTATION AND TESTING
Python Code and Output:
 CONCLUSION

In this project, to improve the accuracy, quality and scalability of movie

recommendation system, a Hybrid approach by unifying content based filtering
and collaborative filtering; using Singular Value Decomposition (SVD) as a
classifier and Cosine Similarity is presented in the proposed methodology. Existing
pure approaches and proposed hybrid approach is implemented on three different
Movie datasets and the results are compared among them. Comparative results
depicts that the proposed approach shows an improvement in the accuracy, quality
and scalability of the movie recommendation system than the pure approaches.
Also, computing time of the proposed approach is lesser than the other two pure
approaches.

Future Scope of the Project

In the proposed approach, It has considered Genres of movies but, in future we can
also consider age of user as according to the age movie preferences also changes,
like for example, during our childhood we like animated movies more as compared
to other movies. There is a need to work on the memory requirements of the
proposed approach in the future. The proposed approach has been implemented
here on different movie datasets only. It can also be implemented on the Film
Affinity and Netflix datasets and the performance can be computed in the future.
 REFERENCES

[1] Hirdesh Shivhare, Anshul Gupta and Shalki Sharma (2015), “Recommender
system using fuzzy c-means clustering and genetic algorithm based weighted
similarity measure”, IEEE International Conference on Computer, Communication
and Control.

[2] Manoj Kumar, D.K. Yadav, Ankur Singh and Vijay Kr. Gupta (2015), “A Movie
Recommender System: MOVREC”, International Journal of Computer Applications
(0975 – 8887) Volume 124 – No.3.

[3] RyuRi Kim, Ye Jeong Kwak, Hyeon Jeong Mo, Mucheol Kim, Seungmin Rho,Ka
Lok Man, Woon Kian Chong (2015),“Trustworthy Movie Recommender System with
Correct Assessment and Emotion Evaluation”, Proceedings of the International Multi
Conference of Engineers and Computer Scientists Vol II.

[4] Zan Wang, Xue Yu*, Nan Feng, Zhenhua Wang (2014), “An Improved
Collaborative Movie Recommendation System using Computational
Intelligence”,Journal of Visual Languages & Computing,Volume 25, Issue 6.

[5] Debadrita Roy, Arnab Kundu, (2013), “Design of Movie Recommendation

System by Means of Collaborative Filtering”, International Journal of Emerging
Technology and Advanced Engineering, Volume 3, Issue 4.

[6] A. Javari, J. Gharibshah, and M. Jalili, "Recommender systems based on

collaborative filtering and resource allocation," Social Network Analysis and
Mining, Vol. 4, No. 1, pp. 234, 2014.

[7] M. Roth, A. Ben-David, D. Deutscher, G. Flysher, I. Horn, A. Leichtberg, and R.

Merom, "Suggesting friends using the implicit social graph," in Proceedings of the
16th ACM SIGKDD international conference on Knowledge discovery and data
mining, ACM: Washington, DC, USA., pp. 233-242, 2010.
[8] M. Li, BM. Dias, I. Jarman, W. El-Deredy, and P.J. Lisboa, "Grocery shopping
recommendations based on basketsensitive random walk," in Proceedings of the 15th
ACM SIGKDD international conference on Knowledge discovery and data mining,
ACM: Paris, France, pp. 1215-1224, 2009.

[9] H. Ma, and H. Liu, "Design of Clothing Clustering Recommendation System on

SOM Neural Network," In 8th International Conference on Social Network,
Communication and Education, Atlantis Press, 2018.

[10] H. Ma, H. Yang, M.R. Lyu, and I. King, "SoRec: social recommendation using
probabilistic matrix factorization," in Proceedings of the 17th ACM conference on
Information.