10 VI June 2022

https://doi.org/10.22214/ijraset.2022.44430
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue VI June 2022- Available at www.ijraset.com

Movie Recommendation System

Jose Immanuvel. J1, Sheelavathi. A2, Priyadharshan. M1, Vignesh. S1, Elango. K1,
1, 3, 4, 5
Unformation Technology, Saranathan College of Engineering, Trichy, India
2
Assistant Professor, Information Technology Saranathan College of Engineering, Trichy, India

Abstract: Movie recommendation system proposed whose primary objective is to suggest a recommended list through singular
value decomposition collaborative filtering and cosine similarity. The present work improves these approaches by taking the
movies’ content information into account during the item similarity calculations. The proposed approach recommends the top n
recommendation list of movies to users on user’s interest preferences that were not already rated. Graphically shows the
percentage of already viewed movies by user and movies recommended to User. Now a day’s recommendation system has
changed the fashion of looking the items of our interest. OTT Movie Application Recommendation for mobile users is crucial. It
performs a complete aggregation of user preferences, reviews and emotions to help you make suitable movies. It needs every
precision and timeliness, however, this can be info filtering approach that’s accustomed predict the preference of that user.
Recommender System may be a system that seeks to predict or filter preferences in keeping with the user’s selections. The very
common purpose where recommender system is applied are OTT platforms, search engines, articles, music, videos etc. during
this work we tend to propose a Collaborative approach-based Movie Recommendation system. It is supported collaborative
filtering approach that creates use of the knowledge provided by users, analyzes them so recommends the flick that’s best suited
to the user at that point.
I. INTRODUCTION
A recommendation system is one type of information filtering system, which filters items by User's interests. In recent decades, the
recommendation system became an inalienable part of ecommerce and social websites due to the problem overload. In an era of
information overloading, recommendation systems have developed for discovering the interesting item according to the User's
preference or choice. It was applied in many areas, such as online learning, e-commerce, etc. Examples of such applications are
YouTube, Amazon.com, Movie Lens, Netflix, Facebook, etc.

II. EXISTING SYSTEM

This model-based C.F. recommendation has been introduced to overcome the challenges of memory-based C.F. These techniques
discover the rating pattern from historical data and give highly accurate and effective recommendations from some sample data.
Clustering model and matrix factorization are familiar techniques used in model-based approaches. SVD, and ALS are popular M.F.
techniques that have gained importance in the Netflix price challenge's recommender system. The existing system works on
individual users' rating and on the genre of the show. This could be someday useless, the users World Health Organization have
completely different completely different style from the recommendations shown by the system as each user might have different
tastes. This technique calculates the similarities between completely different users then suggest show to them as per the ratings
given by the various users of comparable tastes.
III. PROPOSED SYSTEM
In the proposed method, the content based recommendation system, Collaborative based recommendation system and hybrid
recommendation system are used in the proposed method. The past data has been used to build the movies recommendation
systems. This proposes that a rating relying on coordinates of the training set values is applied to the new phase. Computing the
interval between the initial point and each point taken from the training dataset is the initial step. There are different ways to
measure this distance, including different kind of distance such as Euclidean distance, Manhattan Distance and Hamming Distance.
The three mentioned distance calculated using below equations. The very common purpose where recommender system is applied
are OTT platforms, search engines, articles, music, videos etc. during this work we tend to propose a Collaborative approach-based
Movie Recommendation system.We tend to propose economic healthcare associates during this paper the algorithmic rule of the
Film Recommendation supported improved KNN strategy that measures simpler advisory system accuracy. However, to evaluate
performance, the k closest victimized neighbors, the maximum inner circles, as well as the basic inner strategies are used. The
exception to this is the projected results, which use algorithms to check for (supposedly) involvement. The performance results
show that the projected strategies improve additional accuracy of the Movie recommendation system than the other strategies
employed in this experiment.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 2611
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue VI June 2022- Available at www.ijraset.com

IV. SYSTEM ARCHITECTURE

A system architecture is the conceptual model that defines the structure, behavior, and more views of a system. An architecture
description is a formal description and representation of a system, organized in a way that supports reasoning about the structures
and behaviors of the system.

V. SYSTEM DESIGN
A. OTT Recommendation
Movie recommendation system proposed whose primary objective is to suggest a recommended list through singular value
decomposition collaborative filtering and cosine similarity. The present work improves these approaches by taking the movies'
content information into account during the item similarity calculations. The proposed approach recommends the top n
recommendation list of movies to users on user's interest preferences that were not already rated. Graphically shows the percentage
of already viewed movies by user and movies recommended to User.

B. Movie Recommendation
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 behavior.

C. Content Based Filtering

Content-based filtering is a type of recommender system that attempts to guess what a user may like based on that user's activity.
Content-based filtering makes recommendations by using keywords and attributes assigned to objects in a database (e.g., items in an
online marketplace) and matching them to a user profile. For example, a user selects "Entertainment apps" in their profile. Other
features can be implicit, based on the apps they have previously installed. For example, the user installed another app published by
Science R Us. The model should recommend items relevant to this user. In Content-Based
Recommender, we must build a profile for each item, which will represent the important characteristics of that item. For example, if
we make a movie as an item then its actors, director, release year and genre are the most significant features of the movie.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 2612
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue VI June 2022- Available at www.ijraset.com

D. Score Point Matching

The correlation score tells us how close the movies above are related to the movie we provided as an input. Closer its value to 1, the
more chances the user may like the movie recommended by our recommender. The Recommender system recommended “Black
Panther, IT, A Quiet Place, Here diatery...etc.” for the input “Wonder Woman” can be verified in Movie recommendation for given
key words. For the input “Football player trains a woman team” the output returned is “Bigil, What Men Want, The Sensei, Quan li
Kou Sha Etc...” This shows that this feature's result is successful.
RESPONSIVENESS SCORE
(Mean score on a 4-point scale)

Fig 5.4 (a) Responsiveness score

STREAMING SCORE
(Mean score on a 4-point scale)

Fig 5.4 (b) Streaming score

E. Data Analysis
It is very well suited to Data Analysis, Machine Learning (ML) and education. It is a free Jupiter notebook service and does not
require a setup for use, also provides free access to computing resources along with GPUs. For the input “Bigil” output was
successful. The Recommender system tem recommended “Sarkar, Their, Pailwaan, Viswasam...etc.” for the input “Bigil”. For the
input “Wonder Woman” output was successful. The Recommender system recommended “Black Panther, IT, A Quiet Place,
Hereditary...etc.” for the input “Wonder Woman”. Importing the packages and reading the dataset was done. The required dataset.
Genre Count of OTT Platforms Genre Average Rat i ng of OTT Platforms

Fig 5.5 Data analysis

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 2613
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue VI June 2022- Available at www.ijraset.com

F. Rating System
A recommender system, or a recommendation system, is a subclass of information filtering system that seeks to predict the “rating”
or “preference” a user would give to an item. They are primarily used in commercial applications. Factors affecting the reliability of
user review- to-rating conversion are studied. A confidence level is computed for ratings produced from user reviews. The
confidence level is considered in the recommendation formulation process. Use of the confidence level increases prediction
accuracy and user satisfaction.

VI. MODULE LIST

A. Dataset Collection
There are several datasets available to build a movie recommendation system. But for this project, we are going to use a dataset that
contains the metadata (cast, crew, budget, etc..) Of the movie.

B. Preprocessing
The dataset contains two CSV files, credits, and movies. The credits file contains all the metadata information about the movie and
the movie file contains the information like name and id of the movie, budget, languages in the movie that has been released, etc.

C. Content Filtering
Content-based filtering are also known as cognitive filtering. This filtering recommends item to the user based on his past
experience. For example, if a user likes only action movies then the system predicts him only action movies similar to it which he
has highly rated. The broader explanation could be suppose the user likes only politics related content so the system suggests the
websites, blogs or the news similar to that content.

D. Score Point Matching

The user's scoring preferences can also be used to calculate the user's score probability. The scoring value of all commodities in the
score matrix can be regarded as an n- dimensional score vector.What you can do is divide the matrix into training and testing
dataset. For example, you can cut a 4 * 4 submatrix from the lower right end of 10 * 20 matrix. Train the recommendation system
on the remaining matrix and then test it against 4 * 4 cut. You will have the expected output and the output of your system

VII. IMPLEMENTATION
A. Reference Implementation
CPython is the reference implementation of Python. It is written in C, meeting the C89 standard with several select C99 features. It
compiles Python programs into an intermediate bytecode which is then executed by its virtual machine. CPython is distributed with
a large standard library written in a mixture of C and native Python. It is available for many platforms, including Windows and most
modern Unix-like systems. Platform portability was one of its earliest priorities.

B. Other Implementations
PyPy is a fast, compliant interpreter of Python 2.7 and 3.5. Its just-in-time compiler brings a significant speed improvement over
CPython but several libraries written in C cannot be used with it.
Stackless Python is a significant fork of CPython that implementsmicrothreads; it does not use the C memory stack, thus allowing
massively concurrent programs. PyPy also has a stackless version.
MicroPython and CircuitPython are Python 3 variants optimized for microcontrollers. This includes Lego Mindstorms EV3.
RustPython is a Python 3 interpreter written in Rust.

C. Unsupported Implementations
Other just-in-time Python compilers have been developed, but are now unsupported:
Google began a project named Unladen Swallow in 2009, with the aim of speeding up the Python interpreter five-fold by using the
LLVM, and of improving its multithreading ability to scale to thousands of cores, while ordinary implementations suffer from the
global interpreter lock.
Psyco is a just-in-time specialising compiler that integrates with CPython and transforms bytecode to machine code at runtime. The
emitted code is specialized for certain data types and is faster than standard Python code.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 2614
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue VI June 2022- Available at www.ijraset.com

In 2005, Nokia released a Python interpreter for the Series 60 mobile phones named PyS60. It includes many of the modules from
the CPython implementations and some additional modules to integrate with the Symbian operating system. The project has been
kept up- to-date to run on all variants of the S60 platform, and several third-party modules are available. The Nokia N900 also
supports Python with GTK widget libraries, enabling programs to be written and run on the target device.

VIII. CONCLUSION
There are several datasets available to build a movie recommendation system. But for this project, we are going to use a dataset that
contains the metadata (cast, crew, budget, etc...) of the movie. This project an algorithm for collaborative filtering recommendation
system and applied it in the movie recommendation system. This personalized recommendation system uses the singular value
decomposition algorithm and User-based co-coin similarity algorithm; these recommend the top n movies to the active User.

REFERENCES
[1] W. Hill, L. Stead, M. Rosenstein, G. Furnas(1995). Recommending and Evaluating Choices in a Virtual Community of Use. Conference on Human Factors in
Computing Systems.
[2] P. Resnick, N. Iakovou, M. Sushak, P. Bergstrom, J. Riedl, GroupLens: An open architecture for collaborative filtering of netnews, Proc. Comput. Supported
Cooperative Work Conf. (1994).
[3] G. Linden, B. Smith, J. York, Amazon.com
[4] recommendations: Item-to-item collaborative
[5] filtering, IEEE Internet Comput.. 7 (1) (2003) 76-80.
[6] Shuiguang Deng, Dongjing Wang, Ying Li, A recommendation system to facilitate business process modeling, IEEE Trans. Cabernets 47 (6)
[7] L. Yao, Q.Z. Sheng, A.H.H. Ngu, J. Yu, A. Segev, Unified collaborative and content- based web service recommendation, IEEE Trans. Services Comput. 8 (3)
(2015) 453-466.
[8] B. Guo, S. Xu, D. Liu, L. Niu, F. Tan, Y. Zhang. (2017).Collaborative filtering recommendation model with user similarity filling.IEEE 3rd Information
Technology and Mechatronics Engineering Conference (ITOEC) pp. 1151-1154.
[9] J. Bobadilla, F. Ortega, A. Hernando, A. Gutierrez, Recommender systems survey, Knowl.-Based Syst. 46 (1) (2013) 109-132.
[10] J.S. Breese, D. Heckerman, C. Kadie(2013).Empirical analysis of predictive algorithms for collaborative filtering.Vol. 7(7), pp. 43-52.
[11] J. Herlocker, J.A. Konstan, J. Riedl, An empirical analysis of design choices in neighborhoods-based collaborative filtering algorithms, Information Retrieval 5
(4)(2002) 287-310.
[12] J. Das, P. Mukherjee, S. Majumder, P. Gupta (2014).Clustering-based recommender system using principles of voting theory.International Conference on
Contemporary Computing and Informatics (IC3I), Mysore, pp.230-235.
[13] R. Bell, Y. Koren, C. Volinsky, Matrix factorization techniques for recommender systems, Computer 42 (8) (2009) 30-37.
[14] A.B. Barragans-Marti'nez, E. Costa-Montenegro, J.C. Burguillo, M. Rey- Lopez, F. A. Mikic-Fonte, A. Peleteiro, A hybrid content based and item-based
collaborative filtering approach to recommend T.V. programs enhanced with singular value decomposition, Inf. Sci. (Ny) 180 (22) (2010) 42904311.
[15] Luis G. Perez, Francisco Chiclana, Samad
[16] Ahmadi(2011).A Social network representation for Collaborative Filtering Recommender
[17] Systems.International Conference on
[18] IntelligentSystems Design and Applications (ISDA) pp 438-443.
[19] L. Yu, C. Liu, Z. Zhang, Multi-linear interactive matrix factorization, Knowl.-Based Syst. 85 (2015) 307-315.
[20] M.W. Berry, Large-scale sparse singular value computations, Int. J. Supercomput. Appl. 6 (1) (1992) 13-49.
[21] G. Adomavicius, A. Tuzhilin, Toward then extends generation of recommender system.A survey of the
[22] state-of-the-art and possible extensions, IEEE Trans. Knowl. Data Eng. 17 (6) (2005) 734-749.
[23] F.O. Isinkaye,Y.O. Folajimi, B.A. Ojokoh (2015). Recommendation systems: Principles, methods and evaluation. Egypt. Informat. J.
[24] Guangxia Xu, Zhijing Tang, Chuang Ma,Yanbing Liu,Mahmoud Daneshmand (2019).A Collaborative Filtering Recommendation Algorithm Based on User
Confidence and Time Context.Hindawi Journal of Electrical and Computer Engineering. Article ID 7070487, 12 pages.
[25] MovieLens,http://www.grouplens.org/node/73.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 2615