TRIBHUVAN UNIVERSITY

INSTITUTE OF ENGINEERING
LALITPUR ENGINEERING
COLLEGE
DEPARTMENT OF COMPUTER ENGINEERING

THIRD YEAR PROJECT

REPORT ON
DIGITAL MARKET: An Ecommerce Website

SUBMITTED BY:
ASMIT OLI(LEC076BCT043)
AMRIT SAPKOTA(LEC076BCT05)
NISCHAL MAHARJAN(LEC076BCT020)
SAKSHYAM ARYAL(LEC076BCT029)

SUPERVISOR
Er. BINOD SAPKOTA

March 2023
 TRIBHUVAN UNIVERSITY
INSTITUTE OF ENGINEERING
LALITPUR ENGINEERING
COLLEGE
DEPARTMENT OF COMPUTER ENGINEERING

THIRD YEAR PROJECT

REPORT ON
DIGITAL MARKET: An Ecommerce Website
IN PARTIAL FULFILLMENT OF THE REQUIREMENT FOR
THE AWARD OF
BACHELOR DEGREE IN COMPUTER ENGINEERING

SUBMITTED BY:
ASMIT OLI(LEC076BCT043)
AMRIT SAPKOTA(LEC076BCT05)
NISCHAL MAHARJAN(LEC076BCT020)
SAKSHYAM ARYAL(LEC076BCT029)

SUPERVISOR
Er. BINOD SAPKOTA
March 2023
 DECLARATION
We hereby declare that the report of the project entitled “DIGITAL MARKET:
AN ECOMMERCE WEBSITE” which is being submitted to the Department
of Computer Engineering, Lalitpur Engineering College, in the partial
fulfillment of the requirements for the awardof the Degree of Bachelor of
Engineering in Computer Engineering, is a bonafide report of the work carried
out by us. The materialscontained in this report have not been submitted to any
University or Institution for the award of any degree and we are the only author of
this complete work no sources other than those listed here have been used in this
work.

AMRIT SAPKOTA (076/BCT/005)

ASMIT OLI (076/BCT/043)
NISCHAL MAHARJAN (076/BCT/020)
SAKSHYAM ARYAL (076/BCT/029)

i
 CERTIFICATE OF APPROVAL
The undersigned certify that they have read and recommended to the Department of
Computer Engineering, Lalitpur Engineering College, a minor project work entitled
"DIGITAL MARKET: AN ECOMMERCE WEBSITE" submitted by Nischal
Maharjan, Sakshyam Aryal, Amrit Sapkota, and Asmit Oli in partial fulfillment for
the award of Bachelor's Degree in Computer Engineering. The Project was carried out
under special supervision and within the syllabus's prescribed time frame. We found
the students to be hardworking, skilled, and ready to undertake any related work to
their field of study and hence we recommend the award of partial fulfillment of a
Bachelor's degree in Computer Engineering.

Project Coordinator Project Supervisor

Ms. Bisikha Subedi Mr. Binod Sapkota
Department of Computer Department of Computer
Engineering, Lalitpur Engineering Engineering, Lalitpur Engineering
College College

External Examiner Mr. Praches Acharya

Head of the Department (Supervisor),
Department of Computer
Engineering, Lalitpur Engineering
College

II
 COPYRIGHT
The author has agreed that the library, Department of Computer Engineering,
Lalitpur Engineering College, may make this report freely available forinspection.
Moreover, the author has agreed that the permission for extensive copying of this
project work for scholarly purpose may be granted by the professor/lecturer, who
supervised the project work recorded herein or, in their absence, by the head of
the department. It is understood that the recognition will be given to the author of
this report and to the Department of Computer Engineering, Lalitpur Engineering
College in any use of the material of this report. Copying of publication orother
use of this report for financial gain without approval of the Department of
Computer Engineering, IOE, Lalitpur Engineering College and the author’s
written permission is prohibited.
Request for permission to copy or to make any use of the material in this project
in whole or part should be addressed to Department of Computer Engineering,
Lalitpur Engineering College

iii
 ACKNOWLEDGEMENT
First and foremost, we would like to thank our supervisor, Er. Binod Sapkota, who
guided us in doing this project. He provided us with invaluable advice and helped
us in difficult stages. His motivations helped tremendously in the successful
completion of the project.
We are really grateful to our project coordinator, Er. Bisikha Subedi, for advising
us and introducing the project to us in an easy-to-understand way which has
helped us to complete our project easily and effectively on time. We would like to
express our special thanks of gratitude to IOE as well as our principal, Mr. Lallan
Tiwari, who gave us the golden opportunity to do this wonderful project on the
topic, DIGITAL MARKET: An Ecommerce Website, which also helped us in
doing a lot of research and we came to know about so many new things. We are
really thankful to them. Besides, we would like to thank all the teachers who
helped us by advising us and providing the equipment we needed. We are
overwhelmed in all humbleness and gratefulness to acknowledge our depth to all
those who have helped us to put these ideas, well above the level of simplicity and
into something concrete. Also, we would like to thank our family and friends for
their support. Without their support, we wouldn’t have succeeded in completing
this project. Last but not the least, we would like to thank everyone who helped
and motivate us to work on this project.

iv
 ABSTRACT
Our project is Digital Market. This is a website that helps customers to buy and
sell products from different multivendor on the internet. It is useful in the way
that it makes an easier way to buy and sell products online. Digital Market is an
interactive e-commerce solution providing the user with an opportunity to buy
and sell products through an online platform. Digital Market is an online platform
that deals with selling and buying goods. On this website, we have 2 modules.
The first module includes the customer module and the second module includes
the admin module. The customer has to register for any inquiry related to
products. The registered customer can view details of the product and he/she can
buy or sell products of his/her need. He/she has to pay and will get home delivery.
The admin module contains access to the admin page on the website. The admin
can change everything on the website. He can add, delete, and update any
information regarding the product.

Keywords: Merchandise, Multi-vendor

v
 TABLE OF CONTENT
DECLARATION......................................................................................................i
CERTIFICATE OF APPROVAL............................................................................ii
COPYRIGHT.........................................................................................................iii
ACKNOWLEDGEMENT......................................................................................iv
ABSTRACT.............................................................................................................v
TABLE OF CONTENT..........................................................................................vi
LIST OF FIGURES................................................................................................ix
1. INTRODUCTION...........................................................................................1

1.1 Background...............................................................................................1

1.2 Problem Statement....................................................................................1

1.3 Scope.........................................................................................................2

1.4 Objective...................................................................................................2

1.5 System Requirements................................................................................2

1.5.1 Functional Requirements....................................................................2

1.5.2 Non-functional Requirements............................................................3

2. LITERATURE REVIEW................................................................................4

2.1 Existing......................................................................................................4

2.2 Proposed....................................................................................................5

3. FEASIBILITY STUDY...................................................................................6

3.1 Economically Feasibility...........................................................................6

3.2 Operational Feasibility..............................................................................6

3.3 Technical Feasibility.................................................................................6

4. BLOCK DIAGRAM........................................................................................7

4.1 System Overview......................................................................................7

4.2 Use case Diagram......................................................................................8

vi
 4.3 Level 0 DFD..............................................................................................9

4.4 Level 1 DFD............................................................................................10

4.5 Activity Diagram.....................................................................................11

5. METHODOLOGY........................................................................................15

5.1 Dataset Collection...................................................................................15

5.2 Preprocessing..........................................................................................15

5.2.1 Tokenization.....................................................................................16

5.2.2 Stop Words Removal.......................................................................16

5.2.3 Stemming.........................................................................................16

5.3 Feature Extraction...................................................................................17

5.4 Content Based Filtering...........................................................................17

5.4.1 Cosine Similarity Algorithm........................................................18

6. IMPLEMENTATION DETAILS..................................................................19

6.1 Software Development Tools..................................................................19

7. RESULT AND DISCUSSION......................................................................20

7.1 Data Analysis..........................................................................................20

7.2 Experimental Result................................................................................20

7.2.1 Preprocessing................................................................................21

7.2.2 Feature Extraction Process...........................................................21

7.2.3 Cosine Similarity..........................................................................21

7.3 Discussion...............................................................................................22

8. EPILOGUE....................................................................................................23

8.1 Conclusion and Future Enhancement......................................................23

8.2 Limitation................................................................................................23

REFRENCE...........................................................................................................24
vii
APPENDIX A........................................................................................................25

vii
i
 LIST OF FIGURES
Figure 4. 1 System Overview...................................................................................7
Figure 4. 2 Use Case Diagram.................................................................................8
Figure 4. 3 Level 0 DFD..........................................................................................9
Figure 4. 4 Level 1 DFD........................................................................................10
Figure 4. 6 Activity Diagram (Staff's perspective)................................................12
Figure 4. 7 Activity Diagram (Vendors Perspective).............................................13
Figure 4. 8 Activity Diagram (Admin Perspective)...............................................14
Figure 5. 1 Data Processing...................................................................................15
Figure 5. 2 Content Based Filtering.......................................................................18
Figure 7.1 Result of System...................................................................................22
Figure A.1 Product Dataset....................................................................................25
Figure A.2 Tokenized Data....................................................................................25
Figure A.3 Preprocessed data.................................................................................26
Figure A.4 Count Vectorizer..................................................................................26
Figure A.5 Cosine Similarity.................................................................................26
Figure A.6 Sorted Similar data...............................................................................27
Figure A.7 Register................................................................................................27
Figure A. 9 Home Page..........................................................................................28
Figure A.10 Search Box.........................................................................................29
Figure A.11 Product Screen...................................................................................29
Figure A.12 Review...............................................................................................30
Figure A.13 Payment Screen.................................................................................30
Figure A.14 Payment Successful Screen...............................................................31
Figure A.15 User Profile........................................................................................31
Figure A.16 User Management..............................................................................32
Figure A.17 User Profile........................................................................................32
Figure A.18 Django Administration......................................................................33
Figure A.19 User Details.......................................................................................33
Figure A.20 Product Details...................................................................................34
Figure A.21 Product Adding..................................................................................34

ix
Figure A.22 Result of Recommended Product......................................................35
Figure A.23 Datasets for Recommendation...........................................................35

x
1. INTRODUCTION

1.1 Background

A website that allows people to buy and sell physical goods, services, and digital
products over the internet rather than at a brick-and-mortar location. The term
“ecommerce” simply means the sale of goods or services on the internet. In its
most basic form, e-commerce involves electronically transferring funds and data
between 2 or more parties. This form of business has evolved quite a bit since its
beginnings in the electronic data interchange of the 1960s and the inception of
online shopping in the 1990s. Through an e-commerce website, a business can
process orders, accept payments, manage to ship, and provide customer service.
It’s tough to imagine daily life without e-commerce. We order food, clothes,
furniture, and other online services. We download book, music, movies and so
much more. E-commerce has taken root and is here to stay. In this project, a
simple user-friendly website is developed through which we can easily buy and
sell physical goods, services, and digital products. We can get fast, stable and
secure website which will be very helpful to boost a business. The website will be
desktop and mobile friendly which will be easier to use from any devices. There
will be tracker on each and every delivery to make sure costumers get their
product safely.

1.2 Problem Statement

An e-commerce website is a platform that allows businesses to sell their products

or services online. In a project report, potential problems that may arise with an e-
commerce website include security vulnerabilities, usability issues, technical
glitches, limited payment options, slow page loading speed, difficulty in managing
inventory, shipping and logistics challenges, and intense competition from other e-
commerce sites. On the other hand, potential statements could highlight the
convenience and accessibility of online shopping, increased customer
engagement, cost savings through automation, wider market reach, and
opportunities for personalization and customization.

1
1.3 Scope

The proposed project is really good for a long-time online business with our e-
commerce marketplaces. Many Sellers are joining our marketplaces in order to
get more customers for their businesses. We provide the best promotion and
discounts whenever seasonal sales come. The e-commerce sector is really
developing in our countries. Product vendors can increase their business through
our website. Vendor can list the items in almost every category they are interested
to sell. We provide delivery services within 24 to 48 hours. We provide a special
advertising platform through which sellers can advertise their brand not just only
products.

1.4 Objective

The following are the objectives for an e-commerce website:

• To provide a convenient and secure way for customers to make purchases
online.
• To add products to a shopping cart.
• To sell products or services online.

1.5 System Requirements

The following is the desired functionality of the new system. The

proposed project would cover.

1.5.1 Functional Requirements

1.5.1.1 Customer Module

Customers can view/search products without login. Customers can also

add/remove products to the cart without login (if the customer tries to add the
same product in the cart. It will add only one) When a customer tries to purchase a
product, then he/she must log in to the system. After creating an account and login
into the system, he/she can place an order. If customers click the pay button, their
payment will be successful and their order will be placed. Customer can check
their order details by clicking on the orders button. Customers can see the order
status (Pending,

2
Confirmed, and Delivered) for each order. Customer can download their order
invoice for each order Customer can send feedback to admin (without login)

1.5.1.2 Admin Module

Admin can provide a username, email, password, and your admin account will be
created. After login, there is a dashboard where the admin can see how many
customers a registered, how many products are there for sale, and how many
orders placed. Admin can add/delete/view/edit the products. Admin can
view/edit/delete customer details. Admin can view/delete orders. Admin can
change the status of the order (order is pending, confirmed, out for delivery,
delivered). Admin can view the feedback sent by customers

1.5.2 Non-functional Requirements

It specifies the quality attribute of a software system. They judge the software
system based on Responsiveness, Usability, Security, Portability, and other non-
functional standards that are critical to the success of the software system.

1.5.2.1 Availability: The system should remain operational on any day and at any
place.
1.5.2.2 Accuracy: There is a need to optimize the system to ensure more accurate
results and calculations
1.5.2.3 Usability: The system should provide a User-friendly user interface and
tooltips to enhance itself and be effectively responsive.
1.5.2.4 Secure: The system must be able to provide security against any external
injections by using a layered security system. Implementation of user login
functionalities also ensures the system is secure from unauthorized persons.
1.5.2.5 Performance of the system: Response time is very good for a given piece
of work. The system will support a multi-user environment.
1.5.2.6 Reliability of the system: The system will be highly reliable and it
generates all the updated information in the correct order. Data validation and
verification are done at every stage of the activity.

3
2. LITERATURE REVIEW
In this digital era, e-commerce websites are growing day by day by providing
services like buying and selling goods via online. This makes human life easier,
faster and more convenient.

2.1 Existing

Dewi Surya Wuisan

The growth of the internet is altering business practices, notably those in retail
establishments where company models use electronic commerce to handle
transactions. This study's goal is to investigate the best practices for online
advertising implementation and capturing consumer interest in purchasing.
Additionally, this study used a descriptive survey method with verification. With
a sample size of 96 customers, the population in this study consists of Lazada
users in the city of Bandung. The results demonstrate that the use of online
advertising has a direct influence on customers' intent to purchase through the
Lazada website. The rapid development of information technology has had an
impact on the community in supporting various business activities, both large and
small so that they can be widely recognized globally. The most obvious impact is
that apart from being known, it can also increase sales volume and profit. Digital
Marketing is one of the marketing media that has a huge impact. With using
digital marketing in this case is social media, especially in every e-commerce
application to increase sales, especially in the era of globalization social media
affects so sales volume has increased rapidly compared to the old way of selling.
Digital marketing is seen as the best media as the most effective means of
promotion and efficiently and able to increase sales volume significantly.
(Wuisan, 2018) [9].
Zulkarnaen Kedah
The process of purchasing, offering for sale or transferring goods, services, and
information over computer networks is known as electronic commerce (e-
commerce). E-commerce is a subset of e-business, which has a broader definition
that includes business partners, customer support, and job openings in addition to
commercial activities. A database or database (database), e-mail or electronic
mail
4
(e-mail), non-computer technology in the form of different delivery systems, and
a method of payment for e-commerce are additional requirements for e-commerce
in addition to networking technologies. Given that e-commerce is electronic,
customers can access and place orders from many locations. Given the current
state of modern technology, a client wishing to access online shopping need not
physically be there, as there are numerous locations in Indonesia's major cities
that offer Wi-Fi-enabled internet access via laptop, notebook, or Personal Digital
Assistant (PDA). So, this is a crucial time for businesses to establish e-commerce
services. E-commerce is still largely unused in Indonesia. Following some
background information, the author talks about the benefits of e-commerce to his
business goals. (Kedah, 2018)[3].

2.2 Proposed

In this proposed project, vendors will be able to apply for the issuer status by
sending their personal documents such as name, shop name, brand, address, and
representative’s email and phone number. Similarly, the customers will be able to
apply for the issuer status by sending their personal documents such as name,
address, and representative’s email and phone number. After manual verification,
the representative will receive login information to the website. The representative
will then be able to register as a vendor and customer, which will be verified by
the information they provided. Their details will be shown on the website after
they are verified. Admin will be able to log in to our website through provided
username and password. Vendors will be able to log in through provided
username and password and provide product details as well as their pictures.
Customers will be able to watch, buy and review the product. They will be able to
see their order details through our webpage.

5
3. FEASIBILITY STUDY

3.1 Economically Feasibility

The proposed system is an e-commerce website. Python, Django, JavaScript, Git-

hub, and SQL are some of the free and open-source tools we'll be using to build
websites. In the website, there are no costs. By displaying ads, we can generate
income. In light of this, we can state that our project is economically feasible.

3.2 Operational Feasibility

Based on factors including management support, necessary training, labor

reduction, and adverse effects on users and customers, operational feasibility is
determined. The user does not require in-depth knowledge of the website because
the proposed system is interactive. Its UI is user friendly. Additionally,
maintaining this website doesn't require a lot of technical support

3.3 Technical Feasibility

There are variety of technologies available for web development. We have

HTML/CSS and JavaScript as cross-platform frameworks for front-end. For
backend development, we have used d-jango. All the technologies we've used in
our application are supported by large corporations and have a strong community.
Therefore, obtaining any technical support is always simple. The project is
therefore technically feasible.

6
4. BLOCK DIAGRAM

4.1 System Overview

Figure 4. 1 System Overview

The system typically consists of a front-end interface where customers can browse
products, add to a cart, and complete a purchase, as well as a back-end interface
where administrators can manage products, orders, and customer information. The
system may also include features such as search functionality, user accounts,
payment processing, shipping and tracking, and customer support. Overall, This
system is designed to provide a convenient and user-friendly shopping experience
for customers while allowing businesses to efficiently manage their online sales
operations.

7
4.2 Use case Diagram

Figure 4. 2 Use Case Diagram

8
4.3 Level 0 DFD

Figure 4. 3 Level 0 DFD

9
4.4 Level 1 DFD

Figure 4. 4 Level 1 DFD

10
4.5 Activity Diagram

Figure 4. 5 Activity Diagram (Customer’s Perspective)

11
Figure 4. 6 Activity Diagram (Staff's perspective)

12
Figure 4. 7 Activity Diagram (Vendors Perspective)

13
Figure 4. 8 Activity Diagram (Admin Perspective)

14
5. METHODOLOGY

5.1 Dataset Collection

In this project, product data is collected and entered individually in a manual

method, it consists of a CSV file. Our data set has 12 columns and about 200
individual data entries: name, image, brand, category, description, rating, product,
user_id, and price.

5.2 Preprocessing

Data preprocessing is a process of preparing the raw data and making it suitable
for a machine-learning model. It is the first and crucial step while creating a
machine- learning model. A real-world data generally contains noises, missing
values, and maybe in an unusable format, which cannot be directly used for
machine, learning models. Data preprocessing is required tasks for cleaning the
data and making it suitable for a machine-learning model, which also increases the
accuracy and efficiency of a machine-learning model.

Figure 5. 1 Data Processing

15
5.2.1 Tokenization

Tokenization is the process of dividing text into a set of meaningful pieces. These
pieces are called tokens. For example, we can divide a chunk of text into words,
or we can divide it into sentences. Filtering techniques uses white space (blank)
removal and removal of punctuation symbols in tokenizing. All contiguous strings
of alphabetic characters are part of one token; likewise with numbers. Whitespace
characters, such as a space or line break, or by punctuation characters, separate
tokens. Punctuation and whitespace may or may not be included in the resulting
list of tokens. The list of tokens becomes input for further processing such as
parsing or text mining. Tokenization is useful both in linguistics (where it is a
form of text segmentation), and in computer science, where it forms part of
lexical analysis.

5.2.2 Stop Words Removal

Stop words are a part of natural language that does not have so much meaning in a
retrieval system. The reason, for removing stop-words from a text is that they
make the text look heavier and less important for analysts. Removing stop words
reduces the dimensionality of term space. The most familiar words are in text
documents are prepositions, articles, and pro-nouns etc. that does not provide the
meaning of the documents. These words are treated as stop words. Example for
stop words: the, in, a, an, with, etc. Stop words are eliminated from documents
because those words are not considered as keywords in text mining applications.

5.2.3 Stemming

Stemming is the process of producing morphological variants of a root/base word.

Its main use is as part of a term normalization process that is usually done when
setting up information retrieval systems. Stemming programs are commonly
referred to as stemming algorithms or stemmers. A stemming algorithm used is
Porter Stemming. This porter-stemming algorithm reduces the words
“chocolates”, “chocolatey”, “choco” to the root word, “chocolate” and “retrieval”,
“retrieved”, “retrieves” reduce to the stem “retrieve”. Stemming is an
important part of the

16
pipelining process in Natural language processing. The input to the porter
stemmer is tokenized words.

5.3 Feature Extraction

Feature Extraction aims to reduce the number of features in a dataset by creating

new features from the existing ones (and then discarding the original
features). These new reduced set of features should then be able to summarize
most of the information contained in the original set of features. In this way, a
summarized version of the original features can be created from a combination of
the original set.

Here, for this project Count Vectorizer is being used for extraction of product.
This model converts a collection of text documents to a vector of term/token
counts and enables the pre-processing of text data prior to generating the vector
representation.

5.3.1 Count Vectorizer

Count Vectorizer is a great tool provided by the Scikit-learn library in Python. It

is used to transform a given text into a vector based on the frequency (count) of
each word that occurs in the entire text. This is helpful when we have multiple
such texts, and we wish to convert each word in each text into vectors (for using
in further text analysis). Count Vectorizer creates a matrix in which each unique
word is represented by a column of the matrix, and each text sample from the
document is a row in the matrix. This matrix is called sparse matrix. The value of
each cell is nothing but the count of the word in that particular text sample.

5.4 Content Based Filtering

The concept of content-based filtering algorithm. Firstly, the quality of item is

analyzed and after that the properties of product are matched, for this the present
database is used. In Content-based filtering techniques, the product are described
with the help of keywords. Content-based filtering algorithms predict the product
that the user liked in the past and according to the rating of user, the product are
recommended. In Content based filtering the quality of the product or services are
utilized for recommendation. In content-based filtering the system compares the

17
profile of the user with the product, then find similar product, and suggest to the
user.

Figure 5. 2 Content Based Filtering

5.4.1 Cosine Similarity Algorithm

Cosine similarity is a metric used to measure how similar the documents are
irrespective of their size. It measures the similarity using the cosine of the angle
between two vectors in a multidimensional space. It determines whether two
vectors are pointing in roughly the same direction and is often used to measure
document similarity in text analysis.

18
6. IMPLEMENTATION DETAILS

6.1 Software Development Tools

We have used Software Development Tools like Python, JavaScript, Pandas,

PostgreSQL, Redux, React and HTML/CSS in developing our website.

19
7. RESULT AND DISCUSSION

7.1 Data Analysis

This is the explanation of Figure A.1 as we mentioned in the appendix. Data

analysis is the process of inspecting, cleansing, transforming, and modeling data
with the goal of discovering useful information, drawing conclusions, and
supporting decision-making. The first step in data analysis is to define the
problem or question that needs to be answered. Then, data is collected and cleaned
to ensure that it is accurate and relevant to the problem at hand. The data is then
explored and visualized to gain insights into the patterns and trends within the
data. Statistical analysis and machine learning techniques are then used to build
models that can be used to make predictions or identify relationships between
variables. There are many tools and techniques that can be used in data analysis.
For data analysis, we have used python software packages and the Scikit-learn
machine library. We have analyzed all these data using a Jupyter notebook.

7.2 Experimental Result

Firstly, dataset is entered individually in the manual method. Before progressing

to perform any operation on the text data, the data must be pre-processed. Various
processes such as: tokenization, stop word removal, and stemming, have been
carried out to obtain the preprocessed data. After this feature extraction process
has been done, in which Count Vectorizer model has been used. In this model, a
column of the matrix represents each unique word, and each text sample from the
document is a row in the matrix. Now, the Cosine Similarity Algorithm comes
into play. Cosine Similarity is a metric used to measure how similar two items are.
The matrix created using Count Vectorizer is subjected to this metric which
computes the most similar product among all, based upon the product user looked
after.

20
7.2.1 Preprocessing

This is the explanation of Figure A.2 as we mentioned in the appendix of

Tokenized Data. As a first step, the dataset is tokenized into words then, stop
word has been removed. As a stemmer, porter stemmer has been used. While
working with porter stemming, dataset is split according to its attributes. From
entire dataset, each attribute with different tuples is made string without any
whitespaces. After that, all the processed values under different attribute names
are combined together. Then, data named as tags and is saved. Below is the
snapshot of tags of dataset after preprocessing related to this project.
This is the explanation of Figure A.3 as we mentioned in the appendix of
Preprocessed Data. Now, the tag undergoes different encoding processes like
converting each word into lower case word and all. The tags is defined and the
data is processed, which looks like below:

7.2.2 Feature Extraction Process

This is the explanation of Figure A.4 as we mentioned in the appendix of Count

Vectorizer. Once preprocessing has been done, the dataset has been changed into
numerical matrix form, which is realizable for computers. In the Count Vectorizer
process, the words in “tags” are not stored as strings. Rather, they are given a
particular index value. Just like, word ’eat ’would have an index 0, ‘star ’would
have index 1, ‘four ’would have index 2 and so on, in array of matrix.

7.2.3 Cosine Similarity

This is the explanation of Figure A.5 as we mentioned in the appendix of Cosine

Similarity. After the computer realize the dataset, the Cosine Similarity algorithm
is used. The cosine similarity function between a pair of text documents depends
upon the word frequency and number of common words in both text documents.
A longer document has higher word frequencies and higher number of unique
words than shorter documents producing higher similarity to user queries than
shorter documents. So, the cosine similarity values of two text documents in the
training dataset are found. In this, the similarity between two products are
calculated with the help of cosine function. The products are said to be similar if
the cosine angle

21
between two products is smaller. The derived similarity of products in dataset are
shown below:
This is the explanation of Figure A.6 as we mentioned in the appendix of Sorted
Similar Data After, calculating similarity of each product and sorting them
properly. The products with similar context to the product, user has preferred is
recommended.

7.3 Discussion

Figure 7.1 Result of System

The above result showed the list of similar products in reference to product named
"Men's shoes". This recommender system can be used efficiently as it sorts
products according to the cosine angle. The main objective of this system is to
provide the user with the best recommendation of products. For this, a product
similar to all products in the dataset is determined. The dataset contains 195
products and among all this products, four are selected. This four products have
similarity nearly or equal to one.
Here, at first dataset is taken, and then it is tokenized. The processed data is
converted into vectors. The vector contents the context of products on which
cosine similarity algorithm is performed. Now, four products among all is selected
and recommended to the user.

22
8. EPILOGUE

8.1 Conclusion and Future Enhancement

This system is concerned with recommendation of products according to user's

product selection. So, it is mainly concerned with the recommending people,
products of their choice with wish list option to keep the track of the products to
be purchased next. The system has some basic functionalities like rating and
reviewing, searching as well as adding products to cart. This system is designed
for easy availability of products in online platform based on its context. From the
result, it came in conclusion that the result are correct as it can be seen for a
product name Men's Shoes, all products related to it has arrived as its results. In
the future, other functionality can be added too. Like, Product recommendation
based on reviews, locations, etc. which focuses on collaborative filtering can be
implemented. Alternatively, a platform for user-user interaction i.e, Chatbot, etc.
can be added for better user interface. Enhancement of work will help the system
with increased performance as well.

8.2 Limitation

Our system doesn’t have offline buying and selling services. We (users) can’t pay
through other services except e-Sewa/Khalti and cash on delivery. It is not
suitable for perishable commodities like food items.

23
REFRENCE
[1] Andres Felipe Rojas Hernandez, N. Y. (2016, June). Distributed processing
using cosine similarity for mapping big data in Hadoop. Retrieved from IEEE
America Transactions: https://ieeexplore.ieee.org/abstract/document/7555265
[2] Kadim, A. (2018). An Evaluation of Preprocessing Techniques for Text
Classification. International Journal of Computer Science and Information
Security.
[3] Kedah, Z. (2018). Pandawan. Retrieved from Sabda Journal:
https://journal.pandawan.id/sabda/article/view/273
[4] Ramni Harbir Singh, S. M. (2020). Movie Recommendation System using
Cosine Similarity and KNN. International Journal of Engineering and Advanced
Technology, https://www.ijeat.org/wp-
content/uploads/papers/v9i5/E9666069520.pdf.
[5] Rossum, G. v. (1995). Centrum Wiskunde and Information(CWI). Retrieved
from Python reference manual: https://ir.cwi.nl/pub/5008
[7] Sharma, P. (2018, June 21). Comprehensive Guide to build a
Recommendation Engine from scratch(in python).
Retrieved from Analytics Vidhya:
https://www.analyticsvidhya.com/blog/2018/06/comprehensive-guide-
recommendation-engine-python/
[8] Shubham Pawar, P. P. (2022, April). Movies Recommendation System using
Cosine Similarity. Retrieved from International Journal of Innovative Science and
Research Technology:
https://ijisrt.com/assets/upload/files/IJISRT22APR1053_(1).pdf
[9] Wuisan, D. S. (2018). Pandawan. Retrieved from Sabda Journal:
https://journal.pandawan.id/sabda/article/view/275

24
APPENDIX A

Data Analysis

Figure A.1 Product Dataset

Preprocessing Tokenized Data

Figure A.2 Tokenized Data

25
Preprocessed Data

Figure A.3 Preprocessed data

Count Vectorizer

Figure A.4 Count Vectorizer

Cosine Similarity

Figure A.5 Cosine Similarity

26
Sorted Similar Data

Figure A.6 Sorted Similar data

Register

Figure A.7 Register

27
Sign In

Figure A. 8 Sign In

Home Page

Figure A. 9 Home Page

28
Search Box

Figure A.10 Search Box

Product Screen

Figure A.11 Product Screen

29
Review Place

Figure A.12 Review

Payment Screen

Figure A.13 Payment Screen

30
Payment Successful Screen

Figure A.14 Payment Successful Screen

User Profile

Figure A.15 User Profile

31
User Management

Figure A.16 User Management

User Profile

Figure A.17 User Profile

32
DJango Administration

Figure A.18 Django Administration

User Details

Figure A.19 User Details

33
Product Details

Figure A.20 Product Details

Product Adding

Figure A.21 Product Adding

34
Result of Recommended Product

Figure A.22 Result of Recommended Product

Datasets for Recommendation

Figure A.23 Datasets for Recommendation

35