Scribd
Upload
481 views23 pages

Project On Movie Recommendation by Using Data Mining

This document discusses a movie recommendation system that uses data mining techniques. It aims to reduce the time users spend browsing movies by ratings and reviews by directly recommending preferred movies. The system learns from user interactions like searching by movie ratings to improve recommendations. It uses machine learning and data mining approaches like collaborative filtering to store user data and improve performance. Content-based filtering is the technique used, which recommends movies similar to a user's past preferences based on attributes like ratings and views.

Uploaded by

18-5A5 S YESWANTH
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
481 views23 pages

Project On Movie Recommendation by Using Data Mining

This document discusses a movie recommendation system that uses data mining techniques. It aims to reduce the time users spend browsing movies by ratings and reviews by directly recommending preferred movies. The system learns from user interactions like searching by movie ratings to improve recommendations. It uses machine learning and data mining approaches like collaborative filtering to store user data and improve performance. Content-based filtering is the technique used, which recommends movies similar to a user's past preferences based on attributes like ratings and views.

Uploaded by

18-5A5 S YESWANTH
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 23

PROJECT ON MOVIE

RECOMMENDATION BY USING DATA


MINING
ABSTRACT
This is a Movie Recommendation System which will come under most reality for time saving
process.Most of them who watch movie try to admire more on Rating rather than Reviews.They are
few people who think that if rating is good then the movie will be good.These are very commom in
many ways.So to Resolve this situation we use Recommendation System will come under this
situation.This will not only help the user to check the best movie to watch.This will reduce the time
spent on watching each and every movies rating and then checking it.This will directly do the job for
us.Many Most Popular Movie streaming apps do there work easy by this.There are few Techniques
which will help you get your preffered movie in efficient way.In this we will learn and interact on
how does the recommendation system work in the movie recommendation.
They are usually stored in many databases and this can be achieved by ml and data mining.They will
improve the performance in the storing and retrieving.
We have taken only one approach in this project which is enough for the movie recommendation
and most of the time this technique is used.
INTRODUCTION
HOW IT RECOMMENDS?
MECHANISM
WHAT IS MOVIE RECOMMENDATION?
A recommendation system provides
suggestions to the users through a
filtering process that is based on user
preferences and browsing history. The
information about the user is taken as an
input. The information is taken from the
input that is in the form of browsing data.
This information reflects the prior usage of
the product as well as the assigned ratings.
A recommendation system is a platform
that provides its users with various
contents based on their preferences and
likings. A recommendation system takes
the information about the user as an
input. The recommendation system is an
implementation of the 
machine learning algorithms.
MECHANISM
• USERS INTERACT WITH THE INTERNET FOR
MORE INFO ABOUT A MOVIE SO THAT THEY
CAN HAVE MORE FUN WHILE WATCHING.
• WHEN HE/SHE SEARCHES THE KEYWORD
OF THE WITH “RATING” THEN THE SYSTEM
WILL AUTOMATICALLY ALLOCATE SOME
DATABASE FOR IT FOR FUTURE.
• THROUGH ML AND DATAMINING WE CAN
CHANGE THE RANKING OF A MOVIE TO
RECOMMEND ACCORDING TO RATING AND
VIEWS.
• WHEN ANOTHER PERSON TYPES DIFFERENT
MOVIE BUT WITH SAME RATING THIS WILL
ALSO SHOW OTHER MOVIES WITH SAME
RATING
RECOMMENDATION SYSTEM
DIFFERENT FILTERATION STRATEGIES
HOW DO THEY WORK?
RECOMMENDATION SYSTEM
• Simply put a Recommendation System is a filtration program
whose prime goal is to predict the “rating” or “preference” of a
user towards a domain-specific item or item. In our case, this
domain-specific item is a movie, therefore the main focus of our
recommendation system is to filter and predict only those
movies which a user would prefer given some data about the
user him or herself.
CONTENT BASED VS COLLABORATIVE
• This filtration strategy is based on the data provided about the items.
The algorithm recommends products that are similar to the ones that a
user has liked in the past. This similarity (generally cosine similarity) is
computed from the data we have about the items as well as the user’s
past preferences.
• This filtration strategy is based on the combination of the user’s
behavior and comparing and contrasting that with other users’ behavior
in the database. The history of all users plays an important role in this
algorithm. The main difference between content-based filtering and
collaborative filtering that in the latter, the interaction of all users with
the items influences the recommendation algorithm while for content-
based filtering only the concerned user’s data is taken into account.
MORE TYPES OF RECOMMENDATION
SYSTEM
Method For our Approach

Content Based
ARCHITECTURE OF
RECOMMENDATION SYSTEM-Content
Based
DIAGRAM FOR INTERACTION
WORKING OF AZURE SYSTEM IN
CONTENT BASED
• This scenario covers the training and evaluating of the machine learning model using the Spark alternating least squares
 (ALS) algorithm on a dataset of movie ratings. The steps for this scenario are:
1.The front-end website or app service collects historical data of user-movie interactions, which are represented in a table
of user, item, and numerical rating tuples.
2.The collected historical data is stored in blob storage.
3.A Data Science Virtual Machine (DSVM) is often used for smaller workloads to experiment or develop a product based
on a Spark ALS recommender model. The ALS model is trained using a training dataset, which is produced from the
overall dataset by applying a data splitting strategy. For example, the dataset can be split into sets randomly,
chronologically, or stratified, depending on the business requirement. Similar to other machine learning tasks, a
recommender is validated by using evaluation metrics (for example, precision@k, recall@k, MAP, nDCG@k).
4.Azure Machine Learning coordinates the experimentation, such as hyperparameter sweeping and model management.
5.A trained model is saved to Azure Cosmos DB, which can then be applied for recommending the top k movies for a
given user.
6.The model is then deployed onto a web or app service by using Azure Container Instances or Azure Kubernetes Service.
• For an in-depth guide to building and scaling a recommender service, see the article 
Build a real-time recommendation API on Azure.
PRINCIPLE OF RECOMMENDATION
SYSTEM
• Recommendation systems helps users by providing useful suggestions, thus reducing their
search time.
• These recommendations can be generated in various ways like content based, collaborative
filtering, hybrid methods and other approaches.
• In this paper, a movie data-set has been used which contains user ratings for a number movies,
by different users.
• The user ratings are used for classifying data into various categories which can further be helpful
to generate recommendations.
• In this paper, we are going to use data mining techniques to analyse user preferences and
determine user-specific movie ratings through the help of data mining techniques.
• We will use a movie database from IMDB and determine user specific ratings for each of them.
• The analysis of attributes of these movies will help us identify the decisive factors and identify
user preferences accurately
HOW DO IT SEARCH?
PROCESS BEHIND SEARCHING IN NETFLIX
Historically, Netflix has used a template-based
approach to tackle this problem of page
generation i.e. a massive blood bath of rows
competing for precious screen real estate. It is a
task focused on not only accuracy, but also
providing diversity, accessibility and stability at
the same time. Other considerations include
hardware capabilities (what device is being
used) and which rows/columns are visible at
first glance and upon scroll.
With all these requirements, one can see why a
template-based approach can work quite well
for a start because one can have a few fixed set
of criterions to be met at all times. However,
having many of such rules in place naturally
landed Netflix into a local optimum in terms of
providing a good member experience.
NETFLIX RECOMMENDED SYSTEM
• 80% of stream time is achieved through Netflix’s recommender
system, which is a highly impressive number. Moreover, Netflix
believes in creating a user experience that will seek to improve
retention rate, which in turn translates to savings on customer
acquisition (estimated $1B per year as of 2016).
• The solution and approach that Netflix uses is a Machine Learning
one, where they aim to create a scoring function by training a model
using historical information of which homepages they have created for
their members — including what they actually see, how they
interacted with and what they played.
CONTENT BASED RECOMMENDER
SYSTEMender System

A Content-Based Recommender works by the


data that we take from the user, either
explicitly (rating) or implicitly (clicking on a
link). By the data we create a user profile,
which is then used to suggest to the user, as
the user provides more input or take more
actions on the recommendation, the engine
becomes more accurate.
THANK YOU
DWDM LAB
FACULTY-Mrs. N Swapna Goud
BY-S YESWANTH
M ABHILASH
V BHANUPRAKASH
RASWITH
AMAAN ALI

You might also like