BOOK RECOMMENDATION SYSTEM
Prof. Veena Rani
Professor, Malla Reddy University
Hyderabad
veena@mallareddyuniversity.ac.in
Kummari Vamshi
Tummala Sai Vivek Reddy
Student, Malla Reddy University
Student, Malla Reddy University
Hyderabad
Hyderabad
2011cs020169@mallareddyuniversity.ac.in
2011cs020170@mallareddyuniversity.ac.in
Kallepu Akanksha
Student, Malla Reddy University
Hyderabad
2011cs020171@mallareddyuniversity.ac.in
Kura Akhilesh
Student, Malla Reddy University
Hyderabad
2011cs020171@mallareddyuniversity.ac.in
1.ABSTRACT
As we all know that due to covid-19
pandemic it made difficult to go out and find
a required book from many of available
books . Our book recommendation system
has been emerged which is used to
recommend the book in effective manner
from a large number of books with user
interests and ratings. Most of these existing
systems are user-based ratings where
content-based and collaborative based
learning methods are used. These systems'
irrationality is their rating technique, which
counts the users who have already been
unsubscribed from the services and no longer
rate books. This paper proposed an effective
system for recommending books for online
users that rated a book using the clustering
method and then found a similarity of that
book to suggest a new book. The proposed
system used the K-means Cosine Distance
function to measure distance and Cosine
Similarity function to find Similarity between
the book clusters. Sensitivity, Specificity,
and F Score were calculated for ten different
datasets. The average Specificity was higher
than sensitivity, which means that the
classifier could re-move boring books from
the reader's list. The results of book
recommendation system is to recommend the
book in effective manner than the user-based
recommendation system.
2. INTRODUCTION
Recommendation system is defined as the
system is used to recommend the specific
book based on the interests of users and also
based on the ratings which are given by the
people according to their satisfaction on the
purchased books. Finding the right products
at the right time is a real challenge for
consumers. Machine learning has been
improvising the recommendation systems,
additionally it brings a lot of prospects to
boost performance of recommendation
system. Recommendation systems square
have wide custom-made that uses
collaborative filtering and content-based
filtering
severally.
Library
book
recommendation system is the web
application which is used to manage the
library’s repository. It is helpful in preserving
databases for the book purchases which are
available in the library. This system tracks
several categories like books, journals,
magazines, etc.
The fourth industrial revolution
emerges with a technological breakthrough in
the fields like the internet of things (IoT),
artificial intelligence (AI), quantum
computing, etc. The economic boom
improves the living standard of people and
elevates the purchasing power of individuals.
Nowadays, physical visits to shops and
libraries have been drastically reduced due to
their busy schedules and COVID-19
pandemic. Instead, e-marketplaces and elibraries became popular hotspots. E-book
reading platforms and online purchasing
tendencies made users discover their favorite
books from many items. As a result, users
tend to get swift and smart decisions from an
unprecedented amount of choices using
expert systems. Thus, recommendation
systems came into the scene to customize
users' searching and deliver the best-
optimized results from a multiplicity of
options. A recommendation system was
initially proposed by Amazon, which
contributed to raising Amazon's sales from
$9.9 billion to $12.83 billion in 2019 (second
fiscal quarter) that was 29% more than the
previous year. The recommendation systems'
algorithms were usually developed based on
content-based filtering, associative rules,
multi-model ensemble, and collaborative
filtering. Multi-model ensemble algorithms
can be used for recommendation systems, but
content-based filtering needs a massive
amount of real-world data to train the
predictive model. Apriori algorithm is used to
find the association rules and degree of
dependencies among rules. Multiple
classifiers are typical for multi-model based
RS. In that case, two different layers can be
enforced. In the first layer, a few basic
classifiers are trained, and in the second
layer, the basic classifiers are combined by
using ensemble methods like XGBoost or
AdaBoost. A multi-model ensemble
algorithm is also used in spatial pattern
detection. It can calculate the spatial anomaly
correlation with each other and can cluster
the anomaly correlations. The clustering
technique works as a filter to detect spatial
noise patterns. Collaborative filtering filters
items based on the similar reactions. It
searches a large group of people and can
detect a smaller set of users who have a
similar taste for collecting items. The
similarity measure is a significant component
of collaborative filtering. It can find the sets
of users who show the behavior to select
items.
Recommender systems are highly
customized recommendation systems are
collaborative filtering and content based
filtering respectively. In collaborative
filtering, this is also called social filtering
items are selected based on the relationship
between the current user and other system
users. However, content-based filters are
recommended based on user interactions and
preferences User interests are first analyzed
and the result of the user profile analysis is
compared with them items available in the
system to provide user recommendations to
the user. In a general sense, collaborative
filtering involves collaborating large
volumes of multiple view-point, agents, and
sources. It can be applied in mineral
exploration,
weather
forecasting,
ecommerce, and web applications where a
massive volume of data needs to be processed
to make the predictions. The drawback of
collaborative filtering is that it needs a
tremendous amount of user data, which is
realistic for some applications where we do
not use information. On the other hand,
content-based
filtering
use
objects
information and recommendation are made
based on object similarity. Generally,
content-based filtering is useful when we do
not have useful information. The Similarity
among the products is considered while
recommending. Both supervised and
unsupervised machine learning algorithms
are applied to measure the Similarity among
products. The content can be structured,
semi-structured, and unstructured, but it must
be synchronized into a structured format to
calculate the Similarity. A hybrid
recommendation system combines two or
more filtering techniques to produce the
output. The performance of hybrid filtering is
better comparing to collaborative and
content-based
filtering.
Collaborative
filtering does not consider domain
dependencies, and contentbased filtering
does not consider people's preferences. A
combined effort is required from both
collaborative and content-based filtering
techniques to make better predictions. The
combined effort increases the common
knowledge in collaborative filtering with
content data and content-based filtering with
user preferences. Cross-domain filtering
algorithms can access information that
belongs to different domains. Cross-domain
filtering algorithms make predictions by
exploring the source domain and increase the
prediction in the target domain.
Collaborative filtering is a very common
technique for book recommendation. But the
accuracy of this technique was 88% or 89%,
which is comparatively low. However, a
content-based recommendation system needs
an enormous amount of training data set,
which is not feasible for real-world scenarios.
When Jaccard similarity was added with
collaborative filtering, it achieved the highest
recall. The major drawbacks of a
collaborative recommender system are
sparsity and cold-start issues. These issues
can be removed using a kernel-based fuzzy
technique that scored a 95% accuracy rate.
The content-based filtering method was used
to recommend items based on the Similarity
among articles. The major drawback of this
method is that it ignores current users' ratings
when suggesting new items. But user rating
is relevant for recommending new books or
journals. As the user rating information is
missing in the documents, the content-based
filtering has low accuracy in the current book
or journal recommendation. Most of the
systems are powered with Artificial
Intelligence that search items on popularity,
correlation, and content of books .Other
popular techniques for RSs are listed as
influence discrimination model , linear mix
model , transfer meeting hybrid for
unstructured text , pseudo relevance feedback
, fixed effect model , natural language
processing with sentimental analysis ,
opinion leader mining , fuzzy c-mean
clustering , knowledge graph convolution
network, a personal rank algorithm using
neural network , k-nearest neighbor, and
frequent pattern tree . Online search has an
abnormal effect on the recommendation
system. For example, clicking on high
ranking books has no impact but clicking on
low ranking books has a positive impact.
Data sparsity is another major problem for
the traditional book recommendation system,
which can be solved using a personal rank
algorithm using a neural network. Both knearest neighbor and frequent pattern tree are
highly efficient for recommending scientific
journals for academic journal readers.
Moreover, several context-aware rule-based
techniques, and their recent pattern-based
analysis or classification-based techniques or
rule-based belief prediction can be used to
build the recommendation systems. In this
paper, a clustering-based recommendation
system was used to achieve the highest
accuracy.
This paper proposed a clustering-based
book recommendation system that uses
different approaches, including collaborative,
hybrid, content-based, knowledgebased, and
utility-based filtering. Clustering allows
regrouping all books based on the rating and
user preference datasets. Such clustering
shows remarkable prediction capability for a
book recommendation system. The core
target of this research is to model an
improved approach for customizing the
recommendation system.
3. LITERATURE REVIEW
Suggestion is a very common and cold ecommerce issue. Book Recommendation
system performs in multiple ways including
faculty member based on quality of the
project. This article proposes a collective
suggestion filtering system focused on naive
Bayesian
approach.
The
current
recommendation method does have a really
great performance, than numerous prior
implementations, including the praised KNN algorithm being used by suggestion
especially at longer length. In the project we
have used cosine-similarity which is used to
find similarities between two variables.
According
to
both
the
undertake
experimentation, than numerous prior
implementations, including the praised KNN algorithm being used by book suggestion
especially at longer length. System of
suggestion is rapidly increasing that is used
in fields, such as films, traveling, songs,
books etc. Increasing social acts have
increased the use of recommending programs
in persons and community recommending
programs. suggestion structures also address
the issue of fault starts which occurs within a
person recommendation engine.
This work provides a report on the latest
technology relevant to several areas of
optimization algorithms. As for their usage
and customer obvious sign designs, the
scientist addressed prior structures. A
optimization algorithms is quite important to
study project difficulties.
The information in the internet growth is
very major and people need some
instruments to find and sensitive applicable
information. Recommendation systems help
to navigate in a short time and give necessary
information.
4. PROBLEM STATEMENT
A recommendation system is any system that
mechanically suggests content for web site
readers and users. These systems evolve an
intelligent algorithm, which generates
recommendations to users. Machine learning
has been improvising the recommendation
systems, additionally it brings a lot of
prospects to boost performance of
recommendation system. Recommendation
systems square have wide custom-made that
uses collaborative filtering and content-based
filtering severally. It is helpful in preserving
databases for the book purchases. This
system tracks several categories like books,
journals, magazines, etc.
In the recommendation system the problem is
trying to forecast the opinion the users will
have on the dissimilar substance and be able
to recommends the finest items to each user.
Another some problems in recommendation
system are data sparsity. Data sparsity means
the data is widely spread; it has null values
and missing values.
5. EXISTING SYSTEM
A recommendation system is one of the top
applications of machine learning. Every
consumer Internet company requires a
recommendation system like Netflix,
Youtube, a news feed, etc. What you want to
show out of a huge range of items is a
recommendation system.
There are some of the existing book
recommendation engines used by the top
rated book purchasing websites. The existing
engines make use of conventional algorithms
for recommendations.
Content based Recommendation: System
generates recommendations from source
based on the features associated with
products and the user’s information. Contentbased recommenders treat recommendation
as a user-specific classification problem and
learn a classifier for the user's likes and
dislikes based on product features.
Collaborative Recommendation: Suggestions
are generated on the basis of ratings given by
group of people.
Context Based Recommendation: System
requires additional data about the context of
the item consumption like time, mood and
behavioral aspects.
6. METHODOLOGY
The below Fig 1 displays Book
Recommendation System Model flow graph
method. This flow shows the program
operation. Method flow demonstrates how
well the system works, how much the system
handles the relevant data, and how output is
expected by the system.





This deals with three types of data
files users, books and ratings.
Using the numpy, pandas, sklearn and
pickle library the raw datasets is
preprocessed.
The preprocessed datasets are merged
together as single set of data.
The data is splitted into training and
testing datasets for train and test using
machine learning approach.
Tensorflow is used to train the model
and got the training loss and
7. RESULT
Python libraries import: Numpy, Pandas,
sklearn and tensorflow.
The dataset contains three excel files. The
dataset of
2,78,858 users includes
11,49,780 reviews of 2,71,360 books.
The scores are on (1-5) scale.
When the user need particular book then
it recommend the list of books as below.
8. CONCLUSION
validation loss.
Machine learning is statistical process
that builds test models structures
automatically. It is primarily a AI
contingent based on the idea that the
system can test records, understand the
style and make the choices from the
smallest individual intervention. Three
datasets are taken from implementing the
Book Recommendation System. Users,
Books and Ratings datasets preprocessed
for cleaning the datasets for further
implementation. Then the three datsets
are merged using python command and it
splitted into training and testing for
acquiring the accurate output. Using the
recommend command it retrieves the list
of books that user is willing to read or
take. By this way the user is
recommended with their necessary book.
9. REFERENCES
[1]
Ahuja,
R.
(2019).
Movie
Recommender System Using K-Means
Clustering AND K-Nearest Neighbor.
IEEE.
[2] Dara, S. (2019). A survey on group
recommender systems. Journal of
Intelligent Information Systems.
[3] Gao, Y. (2019). Research on Book
Personalized Recommendation Method
Based on Collaborative Filtering
Algorithm. IEEE.
[4] M, I. (2020). Predicting Books’
Overall Rating Using Artificial Neural
Network. International Research Journal
of Engineering and Technology .
[5] Parvatikar, S. (2015). Online Book
Recommendation System by using
Collaborative filtering and Association
Mining . IEEE.
[6]
Ramakrishnan,
G.
(2020).
Collaborative
filtering
for
book
recommendation system. SocProS.
[7]
Shah,
K.
(2019).
Book
Recommendation System using Item
based
Collaborative
Filtering
.
International Research Journal of
Engineering and Technology .
[8] Sohail, S. S. (2013). Book
Recommendation System Using Opinion
Mining Technique . IEEE.
[9] Tan, K. W. (2019). A New
Collaborative Filtering Recommendation
Approach Based on Naive Bayesian
Method. Beijing: ResearchGate.