International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 05 | May 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 4511
A Review on the Role of Machine Learning in Enhancing User
Experience in E-commerce Applications
Tanvi Chadaga
1
, Mahantesh Shivagunde
2
, Jyothi Shetty
3
, Sharvani G S
4
1
Dept. Of Computer Science and Engineering, RV College of Engineering, Bengaluru, Karnataka, India,
2
Dept. Of Computer Science and Engineering, RV College of Engineering, Bengaluru, Karnataka, India,
3
Assistant Professor, Dept. Of Computer Science and Engineering, RV College of Engineering, Bengaluru,
Karnataka, India
4
Associate Professor, Dept. Of Computer Science and Engineering, RV College of Engineering, Bengaluru,
Karnataka, India
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract - Machine Learning is now becoming one of the
leading topics in the technology world. So it comes to no one’s
surprise that leading e-commerce companies would look into
machine learning to incorporate into their commerce
application. User Experience is an important aspect for smooth
business operation since customer satisfaction is the key to
greater productivity. To automise several operations within
the ecommerce application has proven advantageous and
profitable for most business operators. This paper explores
and reviews the various applications of machine learning in e-
commerce as a tool to enhance the user experience.
Key Words: Machine Learning, User Experience, E-
commerce
1. INTRODUCTION
E-commerce stands for Electronic Commerce. It implies
buying and selling goods and services through Electronic
media and the Internet. A more complete definition of E-
commerce is given in [1] : E-commerce is the use of
electronic communications and digital information
processing technology in business transactions to create,
transform, and redefine relationships for value creation
between or among organizations, and between organizations
and individuals.
E-commerce has transformed the way in which
organizations interact with their consumers and partners.
With rapid development in Information and Communication
Technology (ICT), there has been an unprecedented growth
in the E-commerce industry all over the world. According to
studies, global E-commerce sales are expected to reach $4.2
trillion in 2020 and $6.5 trillion by 2023. With increased
number of transactions happening on E-commerce
platforms, organizations have a large corpus of data about
these transactions. This data is being leveraged to improve
the customer satisfaction and User Experience. Artificial
Intelligence (AI), Big Data Analytics (BDA), Data Mining and
Machine Learning (ML) are the tools being used to extract
knowledge from the data which can be used to improve the
User Experience by means of recommendations, dynamic
pricing, optimized search results etc.
1.1 Machine Learning
Propelled by an increase in computational power,
memory, storage and the generation of huge amounts of
data, computers are being employed to perform a wide-
range of complex-tasks with commendable accuracy.
Machine Learning comprises elements of mathematics,
statistics and computer science. It is being leveraged in both
industry and academia to develop intelligent products with
the ability to make accurate predictions using diverse
sources of data[2]. The key beneficiaries of the Machine
Learning and Artificial Intelligence technologies have been
the industries which are able to collect large amounts of data
from their business. The large corpus of data being collected
in E-commerce industries offer tremendous potential to
enhance business opportunities and to improve customer
experience.
Machine learning techniques employ algorithms - a set of
mathematical procedures which describe the relationships
between variables. The primary concern in any Machine
Learning application is an accurate prediction. Given a set of
input features representing the input data, Machine Learning
algorithms try to predict some kind of unknown
characteristic about the input features or find some pattern
from the input data.
The majority of Machine Learning algorithms can be
categorized into two types of learning techniques:
Supervised learning and Unsupervised learning. Supervised
learning refers to a set of Machine Learning algorithms in
which a model is trained on a range of input features which
are associated with a known outcome. In E-commerce this
might represent training a model to relate a customer’s
characteristics (e.g., age, location, purchase history) to
certain outcome (product recommendation). There are two
main types of supervised learning algorithms: Classification
and Regression. Regression is a type of supervised learning
which predicts an output value based on the input features