Scribd
Upload
34 views11 pages

Movie at

Uploaded by

Khushi Tharani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
34 views11 pages

Movie at

Uploaded by

Khushi Tharani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Movie

Recommendation
System

2003209 - Raghav Rathi


2003210 - Meer Kukreja
2003211 - Aniket Lilwani
Mentor - Mrs. Juhi Janjua
Introduction
Recommendation System produces a ranked list of items on which a user
might be intrested, in the context of his/her current choice of an item.A
recommendation system is the information filtering system. The function
of recommeder system is to provide us the best matching information
relevant to our requirement from a bigger
I set of information provided.Our
Recommendation system makes use of the movies watched by a user and
recommends a movie by taking into account of the
overview,crew,cast,etc. Our system uses the concept of Collborative
filtering to generate the desired output.

Recommender Systems has mainly two parts Item and User.


Recommendation Systems

Content - Collaborative Hybrid (CF +


Based Filtering Content Based
Approach (CF) Arppaoch)
Objective
The main objective of our recommendation systems is to provide
recommendations based on viewed information of the users' preferences.
This systems makes uses of information filtering techniques to process
information and provide the user with potentially more relevant items. The
main aim of our project is to provide a highly accurate recommendation
with a clean and a decent UI design making it feasible for any user to use
without any hassles. The proposed system can also be used in variety of
other similar applications like Books, Research Articles, Songs, etc.
Literature Review
Recommendation System is a vast area which is used
everywhere in every field. People use recommendations as
it saves time, so it plays a vital role in various areas. It is
used in many real life applications like Entertainment, E-
Commerce, Services, Social Media etc. Main goal of
recommendation system is to forecast the rating which a
specific user gives to an item. It helps the user to find the
optimum recommendation from the available list of items.
Problem Statement
To build an effective recommender system is also
a challenge because user’s preference keeps on
changing with time. The existing systems don't
have a proper user experience (UX) because it's
very ambiguous and not clean, also too many
pop up's sometimes get annoying for users.
Block Diagram
(1) (2) (3)
Raw Data Pre Processing Model Generation

Website Creation Website Creation

(5) (4)
Collection of Dataset

Discarding Nullified and


incomplete values in
Dataset

Removing unwanted
attributes from dataset

Applying Text Vectorization


and removal of stop words

Generating a Similarity
Matrix by using Cosine
Similarity

Displaying the top 6 Similar


Movie
Algorithm
Content-based Filtering is a Machine Learning technique that uses similarities
in features to make decisions. This technique is often used in recommender
systems, which are algorithms designed to advertise or recommend things to
users based on knowledge accumulated about the user.
This method revolves completely around comparing user interests to product
features. The products that have the most overlapping features with user
interests are what’s recommended. Given the significance of product features
in this system, it is important to discuss how the user’s favorite features are
decided.Two methods can be used Firstly, users can be given a list of features
out of which they can choose whatever they identify with the most. Secondly,
the algorithm can keep track of the products the user has been viewing and
add those features to the users’ data.
Our Proposed System uses Text Vectorization which is the process of converting text into
numerical representation to achieve a numerical similarity between items making it easier
to conclude result. We used Bag of Words (BoW) method to accomplish text vectorization

Formula for Cosine Similarity

The above 2D matrix depicts the similaritymatrix where every matrice element
with value 1 shows similarity between the items with respect to the base item.
In our case,We consider the selected or currently watching movie of the user
as base item and evaluate the matric accordingly.
References
1. https://towardsdatascience.com/cosine-similarity-how-does-it-
measure-the-similarity-maths-behind-and-usage-in-python-
50ad30aad7db

2. https://themoviedb.org

You might also like