GOVERNMENT POLYTECHNIC, AURANGABAD

(An Autonomous Institute of Government of Maharashtra)

“PERSUIT FOR EXCELLENCE”

SEMINAR REPORT ON

“Artificial Intelligence In eCommerce”

SUBMITED
BY

Aaditya Manohar Dhondkar

(Enrolment No. 206009)

GUIDED
BY

Prof. G. U. Jadhav

(Lecturer in Computer Engineering Department)

ACADEMIC YEAR 2022-23 DEPARTMENT OF

COMPUTER ENGINEERING
 GOVERNMENT POLYTECHNIC, AURANGABAD

(An Autonomous Institute of Government of Maharashtra)

CERTIFICATE

This is to certify that Aaditya Manohar Dhondkar has successfully

completed seminar regarding topic “Artificial Intelligence in eCommerce”
during the academic year 2022-2023, in partial fulfilment of Diploma in
Computer Engineering of Government Polytechnic, Aurangabad. To the best
of my knowledge and belief this seminar work has not been submitted
elsewhere.

Date: 05/11/2022

Prof. G U Jadhav Prof. D.S.Sonawane

(Lecturer in Computer Eng.) H.O.D CO

Seminar Guide
 ACKNOWLEDGEMENT

We take an immense pleasure in thanking Prof. S. Ganorkar, the

principal, Government Polytechnic, Aurangabad, our source of inspiration.
We wish to express our deep sense of gratitude to Prof. S. Jaiswal, our
respected Head of Department Computer Engineering, and Prof. G U
Jadhav, my guide for having permitted us to carry out this seminar under his
valuable guidance and useful suggestions, which have helped us in
completing the seminar in time.

I would also like to thank to all our faculty members of our department
for their valuable suggestion in the process of this project work. Finally, yet
importantly, I would like to express our thanks to our beloved parents for their
blessings. Last but never the least; let us thanks our friends and classmates for
their help and co-operation for the successful completion of this seminar.

Mr. Aaditya Manohar Dhondkar

(Enrolment No: 206009)

 INDEX
Sr no Title Page no.

1 Abstract 1

2 Introduction

2.1 What is eCommerce ? 2

3
2.2 What is AI ?

3 Implication of AI in eCommerce 4

3.1 Personalization 5

3.2 Product & Services 6

3.3 Enhance Website 7

3.4 Supply Chain

3.5 Marketing and sales

3.6 Improved Customer Services

4 Applications of AI in eCommerce 8

4.1 Increase in volume of voice Search

9
4.2 Conversational chart bots

10
4.3 Recommendation system of eCommerce

11
4.4 Image Tapping or Image Recognition

5 Algorithm

5.1 Segmentation use for recommendation system 12

6 K means clustering Algorithm 14

 Advantages and Disadvantages of K-means clustering 26

algorithm
7 Future scope 27

8 Conclusion 28

9 References 29

10 PowerPoint Presentation of Seminar 30

 Abstract

The present study, insights on the role of artificial

intelligence in e commerce. Last few years can be dedicated to
e-commerce era with its rapid expansion. At the same time the
technological advances gave rise to different platforms which
can be useful to update the trends and capture the market needs.
Hence this study focuses on the uses of Artificial intelligence in
e commerce business.
This is global era of Artificial intelligence and Machine
Learning. There is great impact of machine learning on society
as we are surrounded with technology. Machine learning and Al
helps us in Searching, Sorting and finding relevant data. Today
all E-commerce giants like Amazon, eBay, and Flipkart standing
on the bleeding edge of Artificial intelligence and Machine
Learning. Artificial Intelligence is really taking over the world.
Al is everywhere now, especially in e- commerce sector Al is
making its impression.

1
 2.Introduction

2.1What is eCommerce?

By definition, eCommerce, also known as electronic

commerce or online retailing, refers to "any type of business, or
profitable transaction which involves the transmission of
information transversely over the internet.
Examples of E-COMMERCE: -
 eBay
 Amazon
 Flipkart
 Snapdeal

2
 First Cry
 BookMyShow

3
 2.2 What is Artificial Intelligence?

Artificial Intelligence also is known as AI is one of the

widest and popular branches of computer science in today’s date
which involved creating and building smart machines.
Artificial intelligence is the simulation of human
intelligence processes by machines, especially computer
systems. Specific applications of AI include expert systems,
natural language processing, speech recognition and machine
vision.
Example of Artificial intelligence in Industry:-

 Manufacturing robots.
 Self-driving cars.
 Smart assistants.

4
  Healthcare management.
 Virtual travel booking agent.
 Social media monitoring.
 Marketing chatbots

3.Implication of Artificial intelligence in eCommerce

Implication of AI in ecommerce:-

 Personalization
 Product & Services

5
  Enhanced Website
 Supply Chain
 Marketing & Sales
 Improved Customer Service

3.1Personalization:-

E-commerce personalization refers to the practice of creating

personal interactions and experiences for customers online.
Personalization can be based on a customer’s previous
purchases, browsing behaviour, geographic location, language e
and other personal information.

Benefits of e-commerce personalization:-

B2C marketers have known this for a while, but personalized
marketing works. With more and more B2B buyers expecting the same
online buying experience that they receive from B2C companies,
providing e-commerce personalization is vital, no matter whether you’re
B2B or B2C.

3.2Product & Services :-

Product & Services in eCommerce using features of AI is Known

as Product Digitization.
Product digitization means adding the digital capabilities to
physical products so that product buyers can interact with the product
and get information in digital format. It is achieved by putting
scannable codes on the product or product packaging. Buyers can scan
the code using their smartphones and access the product information
on their phone screen. Product digitization converts physical products
into digital gateways to convey the right marketing message at the
right moment.

Benefits of product Digitization:-

6
 Digitizing any aspect of business helps you to collect more and
more of business data. Similarly, product digitization helps you to
collect the data of all the stakeholders involved in product’s
journey. And data has become the foundation in taking any
business to the path of success.

3.3 Enhanced Website :-

The role of a website in the eCommerce industry is an online
shop to buy & sell physical goods. However, it sounded hypothetical
before the 1990s. But today, an e-Store is a reality. This is all because of
having ease in online transactions, purchases, window shopping,
inventory management, shipping, and hosting all resources and things that
are essential for enabling a sale & purchase.
Types of e-Commerce Sites :-

 Business-to-consumer(B2C)
 Business-to-business(B2B)
 Business-to-administration(B2A)
 Consumer-to-consumer(C2C)
 Consumer-to-business(C2B)
 Consumer-to-administration(C2A)

3.4 Supply Chain :-

eCommerce supply chain management includes managing the flow

of information, resources and funds among the different entities and stages of
the eCommerce supply chain, from the supply of raw materials to the delivery
of finished products to the buyer.
The entities in the supply chain include the suppliers, producers, vendors,
warehouses, logistics and transportation companies, distribution and fulfilment

7
centre’s and the end buyer. Each entity controls a particular link in the supply
chain and contributes to your overall success or failure in meeting your
customers’ expectations.

3.5 Marketing Sales :-

Ecommerce marketing is the act of driving awareness and
action toward a business that sells its product or service
electronically. Ecommerce marketers can use social media, digital
content, search engines, and email campaigns to attract visitors and
facilitate purchases online.
Supply Chain Management (SCM) is a range of activities
needed to plan, coordinate, schedule and control the procurement,
production, and deliveries of products to customers. SCM is the
backbone of eCommerce and is a very crucial component in its
growth. Supply Chain Efficiency ensures the right product reaches
the right place at the right time. It ensures cost reduction and
enhancement of cash utilization.
3.6 Improved Customer service:-
Conversational AI is solving the problem of answering questions
automatically by leveraging content within the website pages. Also, the
more the user interacts with the AI system, the bot or the assistant or the
AI agent learns more and with every interaction becomes more
intelligent and effective.
Features in eCommerce websites that Improved Customer service :-

 Chatbots
 Customer Feedback System
 Automated order placing System

8
 4.Application of AI in eCommerce:-

1. Increase in volume of voice search

2. Conversational Chatbot’s
3. Recommendation system for eCommerce
4. Image tapping or image recognition

4.1 Increase in volume of voice search:-

Today, people are relying on voice assistants like Alexa,

Siri to know their daily schedule or find out about a product to
buy it online. Loup Ventures1 had released an updated speaker
sales forecast model that had estimated that 75% people in the
US will own a smart speaker, generating $35.5 billion
revenue in 2025. So as more households get hold of this
technology, there are chances of a breakthrough in the
eCommerce businesses. This is definitely an AI application to
keep an eye on in 2021.

9
4.2 Conversational Chat bot's:-

Many top names in different industries like Starbucks,

Sephora, Dominoes have adopted chatbots to benefit their
eCommerce business. The customer can ask any question
regarding a product to a bot and get a prompt response. This can
definitely affect the customer’s decision to make a purchase or
not as they are given quick answers to their queries.
Chatbots are computer programs that simulate human
conversations to create better experiences for customers. Some
operate based on predefined conversation flows, while others
use artificial intelligence and natural language processing (NLP)

10
 to decipher user questions and send automated responses in real-
time.
4.3Recommendation system for eCommerce:-

Recommender systems are used by E-commerce sites to suggest

products to their customers. The products can be recommended
based on the top overall sellers on a site, based on the
demographics of the customer, or based on an analysis of the
past buying behaviour of the customer as a prediction for future
buying behaviour.
A recommendation system, or recommendation
mechanism ,is a tool that uses a series of algorithms, data
analysis and even artificial intelligence (AI) to make
recommendations online.

11
 4.4 Image tapping & Image recognition:-

Image recognition is a type of used to recognize people, places,

objects, logos, and more using pixel and pattern analysis in images. This
type of AI software has become exceptional at recognizing people, with
accuracy exceeding 99%, which is comparable to the ability of humans.
Online shoppers can now simply upload an image of an item they
are searching for and find thousands of products that fulfil their needs
using image recognition . This means there’s no reason to go from store to
store asking an employee which aisle your item is in and then leaving the
store with an item you aren’t satisfied with.

12
 5.Algorithms:-
Segmentations used for recommendation System:-

5.1 Customer demographics: -

Customer demographics are categories of consumer

populations that are useful to a business for purposes, such
as marketing and product design. The term also refers to the
study of such categories in a business context.
For Example:-
 Gender
 Age
 Geographic Location
 Hobbies

13
5.2 Customer lifetime value: -
Customer lifetime value is the total revenue you as an
ecommerce business earn from a customer over time. It takes into account
all their orders ever. It is a good metric to size up customer satisfaction,
loyalty and the viability of a brand.

5.3 Customer behaviour :-

Online consumer behaviour is the process of how consumers

make decisions to purchase products in ecommerce.
Expectations like product availability, delivery transparency,
affordable shipping, and more recently, a convenient buying journey all
affect how consumers make decisions to buy items online (and whether or
not they’ll remain loyal customers once they’ve made a purchase).

5.4 Devices and Channels used :-

An "ecommerce channel" is a route through which an
ecommerce business sells or promotes its goods and services to its
customers. Sales channels are those in which a customer may select and pay
for goods and services. The ecommerce website is an ecommerce sales
channel, as is the mobile App. Marketing channels are used for promotion of
a business, for example pay-per-click advertising (paying to have your
website featured in a search engine's search results) is an example of an
ecommerce marketing channel.
6. K-Means Clustering Algorithm :-

14
 K-Means Clustering is an unsupervised learning algorithm that
is used to solve the clustering problems in machine learning or data
science.
 It is an iterative algorithm that divides the unlabelled dataset into
k different clusters in such a way that each dataset belongs only
one group that has similar properties.
 It is a centroid-based algorithm, where each cluster is associated
with a centroid. The main aim of this algorithm is to minimize
the sum of distances between the data point and their
corresponding clusters.
 The algorithm takes the unlabelled dataset as input, divides the
dataset into k-number of clusters, and repeats the process until it
does not find the best clusters. The value of k should be
predetermined in this algorithm
 The k-means clustering algorithm mainly performs two tasks:-
(i) Determines the best value for K centre points or Centroids
by an iterative process.
(ii)Assigns each data point to its closest k-centre .Those data
points which are near to the particular K-centre ,create a
Cluster

15
How does the K-Means Algorithm Work?
The working of the K-Means algorithm is explained in the below steps:
Step-1: Select the number K to decide the number of clusters.
Step-2: Select random K points or centroids. (It can be other from the input
dataset).
Step-3: Assign each data point to their closest centroid, which will form the
predefined K clusters.
Step-4: Calculate the variance and place a new centroid of each cluster.
Step-5: Repeat the third steps, which means reassign each datapoint to the
new closest centroid of each cluster.
Step-6: If any reassignment occurs, then go to step-4 else go to FINISH.
Step-7: The model is ready.

Let's understand the above steps by considering the visual plots:

16
Suppose we have two variables M1 and M2. The x-y axis scatter plot of these
two variables is given below:

o Let's take number k of clusters, i.e., K=2, to identify the dataset and to
put them into different clusters. It means here we will try to group
these datasets into two different clusters.

o We need to choose some random k points or centroid to form the

cluster. These points can be either the points from the dataset or any
other point. So, here we are selecting the below two points as k points,

17
 which are not the part of our dataset. Consider the below image:

o Now we will assign each data point of the scatter plot to its closest K-
point or centroid. We will compute it by applying some mathematics
that we have studied to calculate the distance between two points. So,
we will draw a median between both the centroids.

18
 o Consider the below image:

From the above image, it is clear that points left side of the line is near to the
K1 or blue centroid, and points to the right of the line are close to the yellow
centroid. Let's colour them as blue and yellow for clear visualization.

19
o As we need to find the closest cluster, so we will repeat the process by
choosing a new centroid. To choose the new centroids, we will
compute the centre of gravity of these find new centroids as below:

20
 Next, we will reassign each datapoint to the new centroid. For this, we
will repeat the same process of finding a median line. The median will
be like below image:

From the above image, we can see, one yellow point is on the left side of the
line, and two blue points are right to the line. So, these three points will be
assigned to new centroids.

21
As reassignment has taken place, so we will again go to the step-4, which is
finding new centroids or K-points.

22
o We will repeat the process by finding the centre of gravity of centroids,
so the new centroids will be as shown in the below image:

23
o As we got the new centroids so again will draw the median line and
reassign the data points. So, the image will be:

24
 o We can see in the above image; there are no dissimilar data points on

either side of the line, which means our model is formed. Consider the
below image:

As our model is ready, so we can now remove the assumed centroids, and the
two final clusters will be as shown in the below image:

25
 Advantages and Disadvantages of K-means clustering
algorithm

1. Advantages :-
o Easy to implement
o With a large number of variables ,K-means may be
Computationally faster than Hierarchical clustering
o K – means may produce tighter clusters than
hierarchical clustering
o An instance can change cluster (move to another
cluster)when the centroids are re-computed

2.Disadvantages :-
o Difficult to predict the number of clusters (k-Value)
o Initial seeds have a strong impact on the final results
o The order of the data has an impact on the final results
o Sensitive to scale: rescaling your datasets(Normalization
Or standardization )will completely change results.
While this itself is not bad, not realizing that you have to
spend extra attention to scaling your data might be bad.

26
 6.Future Scope / Future of AI in eCommerce:-

 Al's development in retail has helped e-commerce businesses reduce

operational costs, boost sales, and increase customer satisfaction. For
instance, some retailers have already successfully implemented
chatbots into their customer service strategy-and it's proving to be a
successful investment. It has also made shopping more convenient for
customers who can now shop at any time of the day or night.

27
 7. Conclusion:-

• AI is on the rise in the e-commerce industry; however, it is still far

from being perfect. E-commerce firms continue to improve their AI
tools to better match market demand

• The benefits of Artificial Intelligence are way more than the one
mentioned above. Understanding that Artificial Intelligence can help
people excel in their high sales and customer relationships in the
ecommerce business, day by day people are getting more drawn
towards AI.

28
 8.References:-
 Emerging Roles of Artificial Intelligence in ecommerce by
Vishal Dinesh Kumar Soni
 Market Segmentation Analysis and Visualization Using K-
Mode Clustering Algorithm for E-Commerce Business. By-
Deepali Kamthania, Ashish Pahwa and Srijit S. Madhavan
 A STUDY ON IMPACT OF ARTIFICIAL INTELLIGENCE
IN E-COMMERCE (Ms J.Prabha, assistant professor,
Department of Commerce)
 Artificial Intelligence (AI) Applications for E-Commerce in
2022
 How online retailers can use algorithms to grow their business
 Clustering algorithms for customer segmentation | by
Sowmya Vivek | Towards Data Science
 K-Means Clustering Algorithm - Javatpoint.
 https://www.divante.com/blog/ai-in-ecommerce-benefits-and-
examples
 https://www.bigcommerce.com/articles/ecommerce/
ecommerce-ai/
 https://medium.com/@Countants/how-artificial-intelligence-
is-transforming-the-e-commerce-industry-countants-scalable-
custom-73ae06836d35

29
30
31
32
33
34
35
36
37
38