USED CAR PRICE PREDICTION

Project Coordinator: Project Guide: Batch Number:D10

Mrs. N. Sujatha Kumari Dr. M. Ramasubramanian 1.T.Shruthi 22D21A05Q0
Assistant Professor Professor 2.D.Ambika Devi 22D21A05L4
3.Saniya 22D21A05P1
CONTENT
Abstract
1. Introduction
1.1 Purpose
1.2 Scope
2.Literature Survey
3. System Analysis
3.1 Existing System & Disadvantages
3.2 Problem Statement
3.3 Proposed System & Advantages
4. System Requirements Specification
4.1 Functional and Non Functional Requirements
4.2 Software Requirements
4.3 Hardware Requirements
4.4 Technologies Used
5. System Design
5.1 Architecture
5.2 System Modules
5.3 DFD’S and UML Diagrams
4. Conclusion
ABSTRACT

With the rapid growth of the number of private cars and the development of the second-hand car
market, second-hand cars have become the main choice when people buy cars. The online second-hand car
platform provides both buyers and sellers the chance of online P2P trade. In such systems, the accuracy of
second-hand car price evaluation largely determines whether the seller and the buyer can get more efficient
trading experience. In this project, the price evaluation model based on big data analysis is proposed, which
takes advantage of widely circulated vehicle data and a large number of vehicle transaction data to analyze the
price data for each type of vehicles by using the optimized BP neural network algorithm. It aims to establish a
second-hand car price evaluation model to get the price that best matches the car.
1.INTRODUCTION
Determining whether the listed price of a used car is a challenging task, due to the many factors that
drive a used vehicle’s price on the market. The focus of this project is developing machine learning models that
can accurately predict the price of a used car based on its features, in order to make informed purchases. We
implement and evaluate various learning methods on a dataset consisting of the sale prices of different makes and
models .
1.1 PURPOSE:
Informed decision-making for buyers and sellers
Competitive pricing and inventory management for dealerships
Risk assessment and accurate valuation.
1.2 SCOPE:
Automotive Industry: Second-hand car price prediction applies to the entire automotive industry, including
dealerships, private sellers, and online marketplaces.
Geographic Location: The scope can be localized to specific regions or countries, or it can be expanded globally.
2.Literature Survey
 Kumar et al. (2019): Proposed a car price prediction model using a combination of machine learning algorithms
such as linear regression, decision trees, and random forests.
 Singh et al. (2020): Developed a car price prediction model using a deep learning approach, specifically a
convolutional neural network (CNN).
 Yadav et al. (2018): Used a support vector machine (SVM) algorithm to predict car prices based on features
such as car make, model, year, and mileage.
 Kaur et al. (2019): Proposed a hybrid approach using both machine learning and deep learning algorithms to
predict car prices.
3.1 EXISTING SYSTEM

 Vehicle valuation services for various vehicle types.

 Provides retail, trade-in, and loan values.

 Provides market value analysis based on current listings.

 Online automotive marketplace with price analysis.

 Analyzes whether a listing is a good deal compared to the market.

DISADVANTAGES OF EXISTING SYSTEM

 Limited Transparency
 Data Out Datedness
 Listing Dependence
 Data Volatility
 Market Fluctuations
 Algorithm transparency
3.2 PROBLEM STATEMENT

 The objective of this project is to develop and evaluate machine learning models that can accurately predict the
price of a used car based on its features. The goal is to assist potential buyers in making informed purchase
decisions by providing an estimated market value for used cars.
 Determining the market price of a used car is challenging due to the multitude of factors that influence it. These
factors can include the car's make, model, year of manufacture, mileage, condition, location, and other specific
features. By leveraging machine learning techniques, we can analyze historical data on car sales and build models
that can predict prices with a reasonable degree of accuracy.
3.3 PROPOSED SYSTEM

 To overcome this problem we have developed a model which will be highly effective. Machine learning
algorithms are used because they provide us with continuous value as an output and not a categorized value.
 Because of which it will be possible to predict the actual price a car rather than the price range of a car. User
interface has also been developed which acquires input from any user and displays the price of a car according to
user’s inputs.
 The first step involves collecting a large dataset of cars, including various features such as make, model, year,
mileage, engine size, fuel type, and historical prices.
ADVANTAGES OF PROPOSED SYSTEM

User-friendly interface:
 Ease of use: the developed user interface is intuitive and user-friendly, allowing users to easily input the
necessary car details without requiring technical expertise.
 Immediate results: users receive instant price predictions based on their inputs, enhancing the user
experience and making the tool highly practical for everyday use.
Adaptability and continuous improvement:
 Model updates: the machine learning model can be continuously updated with new data, improving its
accuracy and adaptability to market changes over time.
 Scalability: the system is designed to scale easily, allowing for the inclusion of new features or
expansion to different types of vehicles without significant rework.
 4. SYSTEM REQUIREMENT
SPECIFICATION
4.1 FUNCTIONAL REQUIREMENTS:
 Data Collection

 Data Preprocessing

 Machine Learning Model

 Price Prediction

 User Interface

 Data Storage & Management

 Performance Monitoring & Updates

NONFUNCTIONAL REQUIREMENTS:
 Performance

 Scalability

 Usability

 Reliability & Accuracy

 Security

 Maintainability

 Portability
4.2 SOFTWARE REQUIREMENTS:
 Operating system : 32 –bit or 64-bit version of windows
and windows 7 or above
 IDE : Visual studio code, Jupiter notebook
 Python : version 3.11.3
 Libraries : SciKit-learn
 Frameworks : Tensor Flow / Keras Or PyTorch

4.3 HARDWARE REQUIREMENTS:

 Processor (CPU) : Intel I7 Or AMD Ryzen 7
 Memory (RAM) : 16 GB Of RAM
 Storage : SSD with at least 512 GB of storage
4.4 Technologies Used:

 Google collab
 PyCharm IDE
 SQL
 RDBMS
 Flask
 5.System Design
5.1 Architecture
COLLECT
DATASET

DATA
FEATURE SELECT THE
PREPROCESSIN
SELECTION COMPANY
G

ENTER THE
NUMBER OF SELECT THE SELECT YEAR SELECT THE
KILOMETERS FUEL TYPE OF PURCHASE MODEL
THAT THE CAR
HAS
TRAVELLED
PREDICT PRIZE
5.2 System Modules

 Data Collection Module:Gather car data (e.g., websites, APIs, databases)

 Data Preprocessing Module:Cleans and preprocesses collected data (e.g., handling missing values, encoding
categorical variables)
 Feature Selection: Choose relevant car features (e.g., car make, model, year, mileage, engine size)
 Machine Learning Model Training Module: Trains machine learning models (e.g., linear regression, decision
trees, random forests) on preprocessed data
 Model Evaluation : Choose the best model (e.g., accuracy, precision, recall).
 Model Deployment Module : Deploy model as web app/API
 User Interface: Create user-friendly interface
 Data Storage: Store and manage data
 Performance Monitoring: Monitor and update model
 Security: Ensure secure access and data protection
5.3 Data Flow Diagram and UML
Diagrams
Take input parameters from Send input to the producer

Car price
User Prediction Car Price
Predictor

Show results to the user The model will predict the best selling price

Data Flow Diagram Level-0

Data Flow Diagram Level-1
testing dataset

Input
Pre-process Data-split
user dataset

training dataset

Display Model Training

result Validation module
Class Diagram
User
+name
+email ID
+password
Data Base
+register()
+name +login()
+email ID +attributes selection()
+password
+store name()
+store email id()
+store password()

Home page
+show attributes
+predict button
+Show attribute option()
+display price()
Use Case Diagram

Register

Login

Verify Login Credentials

Show attributes
Server
Select Attributes

Check attributes
user
Price Prediction

Display Price Admin

Logout
 Client Web Application Server
1:Register
2:Register Confirm
3:Login 4:Search Login Details

Sequence 6:Check login details

5:Login Successful 7:Attributes
Diagram
8:Display Attributes
10:Check Availability

9:Select Attributes

11:Display Price 12:Predict Price

13:Logout
 Deployment Diagram

Database Server
Web Server
Application Server

Login Database
Vehicle Data
Entry Training data set

+Year of Manufacturing
+Kms Driven Testing data set
+Fuel Type
+Showroom Price
Mainframe Computer
Training Module

Model Validation
Used Car Price Prediction

Display Result
Component Diagram
Machine Learning
Algorithms
Data Set
Linear Regression
Data Cleaning Measurements
Kaggle And Normalization
Ridge Regression

Kaggle subset
(for measuring Lasso Regression
Depreciation) Simulated Aging
Random Forest Inference
Regression
Activity Diagram
Start

Collect
Dataset

Data
Preprocessing

Use Machine
Learning Algo

Display
Predicted Price

Stop
6.CONCLUSION

The development of a machine learning-based car price prediction model, featuring a user-friendly
interface, significantly enhances the accuracy and efficiency of estimating car prices. This project integrates
comprehensive data collection, preprocessing, and advanced algorithms to provide precise continuous value
predictions, aiding users in making informed decisions. The user interface simplifies input and delivers
immediate results, while the robust backend ensures scalability and security.
THANK YOU