E-COMMERCE CUSTOMER PREDICTION REGRESSION ANALYSIS USING

PYTHON

ABSTRACT

E-commerce is growing demand in this modern world. In the proposed work, we developed two
robust classifiers namely Linear regression and Decision Tree to predict buying intentions of
users based on past behavior for a large e-commerce website that sells products. In this project,
we reviewed the machine learning approaches, and recent advances in this field. We show that
with sufficient preprocessing and selecting the right feature set, we can good performance under
Regression model than Decision Tree.

OBJECTIVES OF STUDY

Objective of study is to implement e-commerce prediction application with machine learning

algorithm. As the traditional data mining techniques are much effective on implementation, we
used scikit learn and pandas and matplot lib to efficiently handle prediction and plotting the
results. Our aim is to implement two machine learning algorithm and to find the best one among
the implemented algorithms.
INTRODUCTION

E-commerce -- electronic commerce or EC -- is the buying and selling of goods and services, or
the transmitting of funds or data, over an electronic network, primarily the internet. These
business transactions occur either as business-to-business, business-to-consumer, consumer-to-
consumer or consumer-to-business. The terms e-commerce and e-business are often used
interchangeably. The term e-mail is also sometimes used in reference to transactional processes
for online shopping.
HARDWARE REQUIREMENTS

Processor : Any Processor above 500 MHz.

Ram : 4 GB

Hard Disk : 4 GB

Input device : Standard Keyboard and Mouse.

Output device : VGA and High Resolution Monitor.

SOFTWARE SPECIFICATION

Operating System : Windows 7 or higher

Programming : Python 3.6 and related libraries

 SYSTEM ARCHITECTURE

Decision Tree

Dataset Training set

Regression

Learn model
Test set
Model

Test model

Predicted
results
IMPLEMENTATIO N METHODOLOGY

Implementation methodology go through various modules namely dataset collection, data pre-
processing, decision tree implementation and linear regression implementation.

Data set collection

Our dataset contains 500 customers, with the following information for each one:

Features Feature description

Email Customer’s email id

Address Customer’s home address

Avatar Colour selected by customer on their member

profile

Average session length Minutes spent by customer on average for each

in-store session

Time on App Minutes spent by customer on the app

Time on Website Minutes spent by customer on the website

Length of Membership Years the customer has been with Natalie’s

Yearly Amount Spent Money spent yearly by customer on Natalie’s