DPG DEGREE COLLEGE

SUBMITTED BY:

RITIKA SHAH
.
CONTENT
1. ABOUT
2. TYPES OF RECOMMENDATION SYSTEM
3. PROBLEM STATEMENT
4. OBJECTIVE
5. SCOPE
6. REQUIREMENTS
7. LIBRARIES
8. SYSTEM DESIGN
9. OUTPUT
10. CONCLUSION
 ABOUT
Have you ever wondered how YouTube
recommends content, or how Facebook
recommends? Perhaps you’ve noticed similar
recommendations with LinkedIn connections,
or how Amazon will recommend similar
products while you’re browsing. All of these
recommendations are made possible by the
implementation of recommender systems .

Recommender systems help to personalize a

platform and help the user find something
they like.

The easiest and simplest way to do this is to

recommend the most popular items. However,
to really enhance the user experience through
personalized recommendations, we need
dedicated recommender systems.

PI T CH DE CK 4
 TYPES OF RECOMMENDATION
There are basically two types of recommendation system. That are:
SYSTEM
CONTENT-BASED FILTERING COLLABORATIVE FILTERING
This system uses item metadata, such as genre, director, These systems are widely used, and they try to predict the rating
description, actors, etc. for movies, to make these or preference that a user would give an item-based on past
recommendations. ratings and preferences of other users.

8 /0 6 /2 0 XX 5
 PROBLEM STATEMENT
Movie recommendation system provides related content out of relevant and
irrelevant collection of items to users of online service providers. Online
Movie Recommendation System aims to recommend movies to users based on
user-movie item ratings, genre, cast and previous searches or preferences. It
is a web application that allows users to search movies as well as it
recommends them appropriate movies based on their search patterns.

6
 OBJECTIVE
The Movie Recommendation System provides a mechanism to help users categorize users
with similar interests. Basically the purpose of a recommendation system is to search for
material that will be interesting to a person. Moreover, it involves a number of factors to
create personalized lists of useful and interesting content specific to each user/individual.
Recommendation algorithm collects from the user interest. A set of keywords (or
features) of an item is the Item profile.
For example, consider a scenario in which a person goes to buy his favorite cake ‘X’ to a
pastry. Unfortunately, cake ‘X’ has been sold out and as a result of this the shopkeeper
recommends the person to buy cake ‘Y’ which is made up of ingredients similar to cake ‘X’.
  User Preferences: Understand and cater to diverse user preferences, including genres, language, release year,

O and content type (movies, TV shows, documentaries, etc.).

 Personalization: Develop a system that provides personalized recommendations based on individual user

B history, ratings, and watch behavior.

 Scalability: Design a recommendation system that can scale efficiently as the number of users and movies

J increases, ensuring a smooth experience for a growing user base.

 Content Diversity: Ensure that the recommendations offer a diverse set of movies to prevent user boredom

E
and increase the chances of finding content that matches varied interests.

 Real-time Recommendations : Implement a system that can provide real-time recommendations as user
preferences and behavior evolve. .

C  Accuracy and Precision: Focus on improving the accuracy and precision of recommendations by
incorporating advanced algorithms and machine learning techniques.

T  Explainability: Make the recommendation system interpretable by providing explanations for why certain
movies are recommended, increasing user trust and understanding.

I  Cross-Platform Integration: Consider the integration of the recommendation system across various platforms
(web, mobile apps, smart TVs) to enhance user accessibility and experience.

V  Privacy and Security: Address privacy concerns by implementing secure practices for user data handling and
ensuring that the recommendation system complies with relevant data protection
regulations

E  Cost Efficiency: Optimize the recommendation algorithm to balance accuracy with computational efficiency,
8
 SCOPE
WORK ON
SEVERAL RELIEF FROM
NUMBERS OF S AV I N G O F PROCESSOR
D ATA : TIME: PROBLEM:
The number of choices for Many people have problem Many mobile phone and limited

anything on internet is very high selecting the alternative item of processing power computers can’t

and it’s tedious to refine most movie due to lack of time and due handle recommender system due to

to search issues. Also movie its extremely large dataset. The

wanted data by self while
recommendations from friends can solution opted for this can be use of
searching. The scope of this
be time consuming. The system webservices. The proposed system
proposal system includes working
uses web services, thus makes
helps in saving lots of time.
within numerous data, with ease.
process simpler.
9
 TOOLS AND
Requirements TECHNOLOGIES USED
 JUPYTER NOTEBOOK
CASE It is the latest web-based interactive
 Hardware Requirements : TOOLS: development environment for notebooks, code
•Processor: Pentium IV or higher and data. It is a open-source software and users
can use every functionality available for free.
•RAM: 256 MB
•Network: Bandwidth greater than 50
KBps (400 kbps) CLIENT  HTML, CSS and JavaScript is used to
SIDE: make a clean interactive UI

 Software Requirements :
•OS: Windows, iOS, Linux • Python programming language was
•Browser: Chrome, Brave, Mozilla SERVER used as the server-side programming
Firefox, Microsoft Edge, Apple Safari, SIDE: language.
Opera • OS is used for file handling
• NumPy and Pandas were used for array
processing and data framing respectively
10
 Sequence Diagram of Movie
LIBRARIES: recommendation System
 MarkupSafe==1.1.1
 Werkzeug==0.15.5
 numpy>=1.9.2
 scipy>=0.15.1
 scikit-learn>=0.18
 pandas>=0.19
 beautifulsoup4==4.9.1
 jsonschema==3.2.0

8 /0 6 /2 0 XX PI T CH DE CK 11
SYSTEM
DESIGN
OUTPUT

Movies 0 and 4 are more similar to each

other (with a similarity score of 0.23094)
than movies 0 and 3 (score =
0.0377426).The diagonal with 1s suggests
what the case is, each movie ‘x’ is 100%
similar to itself.5.3.3. Output In this web
based movie recommendation application
after opening the home page a pages
displayed in a web browser and in the
text field the movie title ‘The
Avengers’ is entered and enter button is
clicked.

13
After clicking the enter button the user is
redirected to next page with the relevant
output and movie is displayed with details
as shown in the figure
 Once a movie name is searched it will display the movies that are recommended for the user
which are similar as the entered input value by the user on the basis of genre, cast etc.
 These movies are recommended using content based filtering where the similarity scores are
maximum
 C O N C LU S I O N
Recommendation systems have become an important part of everyone’s lives. With the
enormous number of movies releasing worldwide every year, people often miss out one
some amazing work of arts due to the lack of correct suggestion. Putting machine
learning based Recommendation systems into work is thus very important to get the right
recommendations. We saw content-based recommendation systems that although may not
seem very effective on its own, but when combined with collaborative techniques
can solve the cold start problems that collaborative filtering methods face
when run independently. Similarly such systems can be improved further by
applying neural network embedding to uplift the quality of recommendations and make
them more user personalized.

Thus we conclude that studying various approaches towards recommendation engine is

vital to come up with a collaborative engine that overcomes the shortcomings of these
independent approaches and multiplies their benefits. Where independent
approaches towards a movie recommendation system may have shortcomings, when
combined the right way they will help users get the accurate recommendations for movies
17