USED CAR PRICE PREDICTION

ML Report
Submitted in the partial fulfillment of the
requirements for the award of the degree of

Bachelor of Technology in

Department of Computer Science and Engineering

By

Vignesh Mantha 2010030253

Varun krishna 2010030106
K Puneeth 2010030136

Hussain Mazeen 2010030266

Venkat Abhinav 2010030179

under the supervision of

Dr. Pramod patro
Assistant professor

Department of Computer Science and Engineering

K L University Hyderabad,
Aziz Nagar, Moinabad Road, Hyderabad – 500 075, Telangana, India.
March, 2022
 Declaration

The ML Report entitled “USED CAR PRICE PREDICTION” is a record of bonafide

work of Vignesh Mantha 2010030253, Hussain Mazeen 2010030266, Venkat
Abhinav 210030179, Varun krishna 2010030106, K Puneeth 2010030136 submitted
in partial fulfillment for the award of B. Tech in the Department of Computer Science
and Engineering to the K L University, Hyderabad. The results embodied in this
report have not been copied from any other Departments/ University/ Institute.
 Certificate

This is to certify that the AI for DS report entitled “USED CAR PRICE
PREDICTION” is Vignesh Mantha 2010030253, Hussain Mazeen 2010030266,
Venkat Abhinav 210030179, Varun krishna 2010030106, K Puneeth 2010030136
submitted in partial fulfillment for the award of B.Tech in CSE to the K L University,
Hyderabad is a record of bonafied work carried out under our guidance and
supervision.
The results embodied in this report have not been copied from any other
departments/ University/Institute.

Signature of the Supervisor

Dr. Pramod patro
Assistant Professor

Signature of the HOD Signature of the External Examiner

 ACKNOWLEDGEMENT

First and foremost, we thank the lord almighty for all his grace & mercy showered
upon us, for completing this Social Internship successfully.

We take grateful opportunity to thank our beloved Founder and Chairman who has
given constant encouragement during our course and motivated us to do this Social
Internship. We are grateful to our Principal Dr. L. Koteswara Rao who has been constantly
bearing the torch for all the curricular activities undertaken by us.

We pay our grateful acknowledgement & sincere thanks to our Head of the
Department Dr. Chiranjeevi Manike for his exemplary guidance, monitoring, and constant
encouragement throughout the course of the Social Internship. We thank Mrs. Anuradha of
our department who has supported throughout this Social Internship holding a position of
supervisor.

We whole heartedly thank all the teaching and non-teaching staff of our department
without whom we won’t have made this Social Internship a reality. We would like to extend
our sincere thanks especially to our parent, our family members and friends who have
supported us to make this Social Internship a grand success.
 ABSTRACT

 Predicting the cost of a used car in India

 Deciding whether a used car is worth the posted price when you see listings
online can be difficult. Several factors, including mileage, make, model, year, etc.
can influence the actual worth of a car. From the perspective of a seller, it is also a
dilemma to price a used car appropriately. Based on existing data, the aim is to
use machine learning algorithms to develop models for predicting used car prices.
 Deliverables
 Build a linear regression model to predict the prices of used cars.
 Generate a set of insights and recommendations that will help the business.
 TABLE OF CONTENTS

S.No Topic
1 Existing Work

2 Proposed Work

3 Data sets

4 Methodology

5 Output

6 Conclusion

7 Future Enhancement

8 Reference
 Existing Work
The USED CAR PRICE PREDICTION helps the user to get an estimation of a car
of any choice more effectively and efficiently.
 Problem Statement

 Predicting the cost of a used car in India

 Deciding whether a used car is worth the posted price when you see
listings online can be difficult. Several factors, including mileage,
make, model, year, etc. can influence the actual worth of a car.
From the perspective of a seller, it is also a dilemma to price a used
car appropriately. Based on existing data, the aim is to use machine
learning algorithms to develop models for predicting used car
prices.
 Deliverables
 Build a linear regression model to predict the prices of used cars.
 Generate a set of insights and recommendations that will help the
business.

 It is the process useful step by which we manipulate the raw data

and making it
 suitable for research on machine learning models. To understand the
dataset, we
 have to use charts to plot data like the histogram of the data. It is
founded that
 the dataset had a large number of outliers because of the huge
number of values
 of used cars. The car models which are having the latest
manufacturing year and
 low mileage (km driven) are having premium sell. However, there
were few other
 factors like accident history and condition that did not confirm this
premium sell.
 The table shows our dataset in fig1. This dataset was used to
remove outliers
 using 3 standard deviations or moments to calculate the central
tendency around
 the mean origin.
 MODULES

1. Mileage - The standard mileage offered by the

car company in kmpl or km/kg
2. Engine - The displacement volume of the
engine in CC.
3. Power - The maximum power of the engine in
bhp.
4. Seats - The number of seats in the car.
5. New_Price - The price of a new car of the
same model.
6. Price - The price of the car (target)
 Implementation & Methodology

 The Pre-owned cars or so-called used cars have

capacious markets across the globe. Before
acquiring a used car, the buyer should be able to
decide whether the price affixed for the car is
genuine. Several facets including mileage, year,
model, make, run and many more are needed to
be considered before getting a hold of any pre-
owned car. Both the seller and the buyer should
have a fair deal. This paper presents a system
that has been implemented to predict a fair price
for any pre-owned car. The system works well to
anticipate the price of used cars for the Mumbai
region. Ensemble techniques in machine learning
namely Random Forest Algorithm, eXtreme
Gradient Boost are deployed to develop models
that can predict an appropriate price for the used
cars. The techniques are compared so as to
determine an optimal one. Both the methods
provided comparable performance wherein
eXtreme Boost outperformed the random forest
algorithm. Root Mean Squared Error of random
forest recorded 3.44 whereas eXtreme Boost
 displayed 0.53.

OUTPUT:-
 CONCLUSION

• The Pre-owned cars or so-called used cars have capacious markets across the globe. Before
acquiring a used car, the buyer should be able to decide whether the price affixed for the car is
genuine. Several facets including mileage, year, model, make, run and many more are needed to be
considered before getting a hold of any pre-owned car. Both the seller and the buyer should have a
fair deal. This paper presents a system that has been implemented to predict a fair price for any pre-
owned car. The system works well to anticipate the price of used cars for the Mumbai region.
Ensemble techniques in machine learning namely Random Forest Algorithm, eXtreme Gradient
Boost are deployed to develop models that can predict an appropriate price for the used cars. The
techniques are compared so as to determine an optimal one. Both the methods provided comparable
performance wherein eXtreme Boost outperformed the random forest algorithm. Root Mean
Squared Error of random forest.
 Future Enhancement
1. Be consistent. ...
2. Manage proactively. ...
3. Learn the operation by doing the work yourself. ...
4. Prioritize staff retention. ...
5. Keep your eye on customer satisfaction. ...
6. Improve the customer experience. ...
7. Take word-of-mouth seriously. ...
8. Invest in advertising.

REFERENCE:-
Google.com