Mini Project on

Car Price Prediction Analysis

Report Submitted to
Jawaharlal Nehru Technological University Anantapur, Ananthapuramu
in Partial Fulfilment of the Requirements for the Award of the degree of

BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND SYSTEMS ENGINEERING

Submitted by
THIRUVIDHI REVANTH 21121A15B2
Y. V. PUNEETH SETTY 21121A15B9
BOYA SURENDRA 22125A1502
KUPPAM SRINIVAS 22125A1506
PERUGU CHARAN RAJ 22125A1511

Under the supervision of

Mr. B. Venkata Sivaiah, M.Tech.
Assistant Professor
Department of Data Science

Department of Computer Science and Systems Engineering

SREE VIDYANIKETHAN ENGINEERING COLLEGE
(AUTONOMOUS)
(Affiliated to JNTUA, Ananthapuramu, Approved by AICTE, Accredited by NBA & NAAC)
Sree Sainath Nagar, Tirupati – 517 102, A.P., INDIA
2024-2025
 Department of Computer Science and Systems Engineering
SREE VIDYANIKETHAN ENGINEERING COLLEGE
(AUTONOMOUS)
(Affiliated to JNTUA, Ananthapuramu, Approved by AICTE, Accredited by NBA & NAAC)
Sree Sainath Nagar, Tirupati – 517 102, A.P., INDIA

Certificate
This is to certify that, the mini project report entitled
Car Price Prediction Analysis
is the bonafide work done by
THIRUVIDHI REVANTH 21121A15B2
Y.V.PUNEETH SETTY 21121A15B9
BOYA SURENDRA 22125A1502
KUPPAM SRINIVAS 22125A1506
PERUGU CHARAN RAJ 22125A1511

in the Department of Computer Science and Systems Engineering, Sree

Vidyanikethan Engineering College (Autonomous), Sree Sainath Nagar, Tirupati and is
submitted to Jawaharlal Nehru Technological University Anantapur, Ananthapuramu
for partial fulfilment of the requirements of the award of B.Tech degree in Computer Science
and Systems Engineering during the academic year 2024-2025.

Supervisor: Head of Department:

Mr. B. Venkata Sivaiah, M.Tech. Dr. Pradeep Kumar Gupta, M.Tech., Ph.D.
Assistant Professor Professor
Department of Data Science Department of Data Science
Mohan Babu University Mohan Babu University
Sree Sainath Nagar, Tirupati – 517 102 Sree Sainath Nagar, Tirupati – 517 102

INTERNAL EXAMINER EXTERNAL EXAMINER

 DECLARATION

We hereby declare that this project report titled “Car Price Prediction
Analysis” is a genuine work carried out by us, in B.Tech (CSSE) degree course
of Jawaharlal Nehru Technological University Anantapur and has not been
submitted to any other course or University for the award of any degree by us.

We declare that this written submission represents our ideas in our own words
and where others’ ideas or words have been included, we have adequately cited
and referenced the original sources. We also declare that we have adhered to all
principles of academic honesty and integrity and have not misrepresented or
fabricated or falsified any idea / data / fact / source in our submission. We
understand that any violation of the above will cause for disciplinary action by
the Institute and can also evoke penal action from the sources which have thus
not been properly cited or from whom proper permission has not been taken
when needed.

Signature of students
1.

2.

3.
 TABLE OF CONTENTS
Title Page Number
Abstract 1
Introduction 2
Objectives 4
Problem Definition and Requirements 5
Data Collection and Preprocessing 6
Implementation 7
Results and Evaluation 9
Conclusions and Future Work 10
References 11
 LIST OF FIGURES
Figure Name Page Number
Predicted vs Actual Car Prices 9
 ABSTRACT
This project aims to develop a car price prediction analysis using R programming language.
With the increasing availability of car data, predicting car prices accurately has become a
crucial task for both buyers and sellers. Utilizing machine learning techniques, particularly
linear regression, this project seeks to provide insights into the factors influencing car prices
and build a predictive model to estimate car prices based on various features. The project
begins by loading necessary libraries such as ggplot2, dplyr, and caret to facilitate data
manipulation, visualization, and model training. A dataset containing information about car
attributes and corresponding prices is imported and explored using summary statistics and
data structure examination. Missing values are handled through removal to ensure data
integrity. Following data preprocessing, the dataset is divided into training and testing sets
using the caret package's create Data Partition function. This partitioning ensures that the
model is trained on a subset of the data and evaluated on unseen data to assess its
generalization performance. A linear regression model is trained using the training data, with
car price as the dependent variable and various car attributes (e.g., mileage, year, brand, etc.)
as independent variables. The lm function in R is employed to fit the model, capturing the
relationship between the predictor variables and the target variable. To evaluate the
performance of the trained model, predictions are generated on the test data, and evaluation
metrics including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-
squared (R^2) are calculated. These metrics provide insights into the model's accuracy and its
ability to explain the variance in car prices. The project concludes with a visualization of
predicted versus actual car prices using ggplot2. This visualization allows for a visual
assessment of how well the model's predictions align with the true prices across the range of
observed values.

Keywords: Decision Support, Business Intelligence, Demand Forecasting, Regression

Analysis, Trend Analysis, Scenario Analysis, Sales Performance, Economic Indicators,
Competitor Analysis, Predictive Analytics Forecasting Models, Predictive Modeling, Time
Series Analysis Data Mining, Feature Engineering, Market Trends, Forecast Accuracy.

1
 INTRODUCTION

In today's automotive market, the ability to accurately predict car prices is invaluable for both
buyers and sellers. For buyers, it provides insights into fair market value, enabling informed
purchasing decisions. For sellers, it aids in setting competitive prices to maximize profits.
With the proliferation of car data, advanced analytical techniques, particularly those within
the realm of machine learning, have emerged as powerful tools for predicting car prices. This
project aims to develop a car price prediction analysis using R programming language. R is a
widely-used open-source statistical programming language known for its rich ecosystem of
packages tailored for data analysis and machine learning tasks. By leveraging R's capabilities,
this project seeks to explore the intricate relationships between various car attributes and
prices, ultimately building a predictive model to estimate car prices with accuracy. The
project begins by acquiring a dataset containing comprehensive information about car
features such as mileage, year, brand, model, engine type, and more, along with
corresponding prices. This dataset serves as the foundation for our analysis, providing the
necessary inputs for training and evaluating our predictive model. Data pre-processing is a
critical step in any data analysis project, and this project is no exception. The dataset is
carefully cleaned and transformed to handle missing values, outliers, and categorical
variables. By ensuring data quality and consistency, we lay the groundwork for building a
robust predictive model.

Next, the dataset is divided into training and testing sets, following best practices in machine
learning model development. The training set is used to train the predictive model, while the
testing set is reserved for evaluating its performance. This partitioning strategy enables us to
assess the model's ability to generalize to unseen data, a crucial aspect of model validation.
With the data prepared and split, we proceed to train a predictive model using linear
regression, a foundational technique in statistical modelling. Linear regression enables us to
capture the relationship between independent variables (car attributes) and the dependent
variable (car price) by fitting a linear equation to the observed data. Through model training,
we aim to uncover the underlying patterns and trends in the data that drive car prices. Once
the model is trained, we evaluate its performance using established metrics such as Mean
Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R^2). These
metrics provide insights into the model's accuracy, precision, and ability to explain the
variance in car prices. A thorough evaluation ensures that our predictive model meets the
desired performance standards and can be relied upon for practical applications,

2
Finally, we visualize the predicted versus actual car prices to gain a deeper understanding of
how well our model performs across the spectrum of observed values. Visualization aids in
interpreting the model's predictions and identifying potential areas for improvement. In
conclusion, this project demonstrates the application of R programming for car price
prediction analysis, showcasing the power of machine learning techniques in extracting
insights from complex datasets. By accurately predicting car prices, this analysis empowers
stakeholders in the automotive industry to make informed decisions and optimize their
operations.

Stay tuned as we delve into the specifics of data preprocessing, model training, evaluation,
and visualization in subsequent sections, offering a comprehensive overview of our car price
prediction analysis project through R programming.

3
 OBJECTIVES

1. Develop a Predictive Model: Create an accurate predictive model using R programming

to estimate car prices based on various attributes like mileage, year, brand, and more.
2. Analyze Factors Influencing Car Prices: Identify and explore the key factors that
significantly impact car pricing and quantify their influence using statistical techniques.
3. Perform Data Preprocessing: Ensure data quality by cleaning the dataset, handling
missing values and outliers, and transforming categorical variables as required for model
training.
4. Partition Data for Training and Testing: Split the dataset into training and testing
subsets to ensure the model’s generalization ability and reliability on unseen data.
5. Implement Linear Regression Techniques: Use linear regression as the primary
modeling approach to understand and predict the relationship between car attributes and
their prices.
6. Evaluate Model Performance: Assess the predictive accuracy of the model using metrics
such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared
(R²).
7. Visualize Predictions: Utilize data visualization techniques (e.g., predicted vs. actual car
prices) to interpret model results and identify potential areas for improvement.
8. Enhance Decision-Making: Provide stakeholders (buyers and sellers) with insights and
tools to make informed decisions regarding car pricing.
9. Leverage R Programming Tools: Showcase the use of R programming and its powerful
libraries (ggplot2, dplyr, caret) for data analysis, visualization, and predictive modeling.
10. Contribute to the Automotive Industry: Enable stakeholders in the automotive sector to
optimize pricing strategies and enhance operational efficiency through data-driven
insights.

4
 PROBLEM DEFINITION AND REQUIREMENTS

Problem Definition

In the automotive market, accurately determining car prices is a complex challenge due to the
diverse factors influencing pricing. Buyers require reliable price estimates to make informed
purchasing decisions, while sellers must set competitive yet profitable prices to stay ahead in a
dynamic marketplace. Traditional pricing methods often fall short of addressing the intricacies
of car valuation, which involves variables such as mileage, year, brand, and engine type.
Additionally, issues like missing data, outliers, and inconsistencies in real-world datasets
complicate the predictive process. These challenges emphasize the need for advanced
analytical techniques to accurately model and predict car prices, ensuring reliable insights for
all stakeholders.

Requirements

Functional Requirements

The project requires acquiring and preparing a comprehensive dataset containing car attributes
and corresponding prices. The data must be cleaned and preprocessed to handle missing
values, outliers, and inconsistencies, ensuring its suitability for modeling. A predictive model
will be developed using R programming, with linear regression employed to establish the
relationship between car attributes and prices. The dataset will be divided into training and
testing subsets to validate the model's generalization ability. Performance metrics such as
Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²) will be
used to evaluate the model's accuracy. Finally, visualizations will be created to assess and
interpret the predictions effectively.

Non-Functional Requirements

The project must ensure a high level of accuracy and reliability in predictions, with minimal
errors and consistent performance across different datasets. Scalability is essential to
accommodate larger datasets and additional features in the future. Usability is critical, as the
outputs must be easily interpretable and actionable for end-users, including buyers and sellers.
Leveraging R libraries such as ggplot2, dplyr, and caret is necessary to streamline data
manipulation, visualization, and modeling. Overall, the project must deliver a robust, efficient,
and user-friendly car price prediction solution that meets the needs of the automotive market.

5
 DATA COLLECTION AND PREPROCESSING

The foundation of the car price prediction project lies in acquiring a comprehensive dataset
containing essential car attributes such as mileage, year, brand, engine type, and their
corresponding prices. This dataset serves as the primary input for the analysis and modeling
process. Once collected, the data undergoes thorough preprocessing to ensure its suitability for
predictive modeling. Preprocessing begins with handling missing values, which are either
removed or imputed depending on their impact on the dataset's integrity. Outliers are
identified and treated to prevent distortion of the model’s results. Categorical variables, such
as car brand or model, are transformed into numerical representations through encoding
techniques to make them compatible with machine learning algorithms. Additionally, the data
is standardized or normalized as needed to maintain consistency across features with varying
scales. This preprocessing stage is crucial for eliminating errors, ensuring data quality, and
creating a clean and robust dataset that enhances the accuracy and reliability of the predictive
model.

6
 IMPLEMENTATION

Packages:
 readr
 dplyr
 ggplot2
Source Code:
# Install necessary packages (run only if packages are not already installed)
install.packages("ggplot2")
install.packages("dplyr")
install.packages("caret")

# Load necessary libraries

library(ggplot2)
library(dplyr)
library(caret)

# Load the dataset

data <- read.csv("car_dataset.csv")

# Explore the dataset

head(data)
summary(data)
str(data)

# Preprocess the data

# Remove rows with missing values
data <- na.omit(data)

# Split the data into training and testing sets

set.seed(123) # for reproducibility
train_index <- createDataPartition(data$Price, p = 0.8, list = FALSE)
train_data <- data[train_index, ]
test_data <- data[-train_index, ]

7
# Train a linear regression model
lm_model <- lm(Price ~ ., data = train_data)

# Evaluate the model

predictions <- predict(lm_model, newdata = test_data)
mse <- mean((predictions - test_data$Price)^2)
rmse <- sqrt(mse)
rsq <- cor(predictions, test_data$Price)^2

# Print evaluation metrics

cat("Mean Squared Error (MSE):", mse, "\n")
cat("Root Mean Squared Error (RMSE):", rmse, "\n")
cat("R-squared (R^2):", rsq, "\n")

# Visualize the predicted vs. actual prices

ggplot() +
geom_point(data = test_data, aes(x = Price, y = predictions), color = "blue") +
geom_abline(intercept = 0, slope = 1, color = "red") +
labs(x = "Actual Price", y = "Predicted Price") +
ggtitle("Predicted vs. Actual Prices")

8
 RESULTS AND EVALUATION

Figure 1. Predicted vs Actual Car Prices

Here is the graph showing the predicted car prices versus the actual car prices. The red
dashed line represents the ideal scenario where the predicted prices perfectly match the actual
prices. Points closer to this line indicate better predictions by the model.

9
 CONCLUSIONS AND FUTURE WORK

Conclusion

The car price prediction model developed has shown effective performance in estimating car
prices based on key features such as make, model, year of manufacture, mileage, and other
important attributes. The model leverages machine learning algorithms to identify patterns
and relationships between these features and the actual market prices. Despite achieving
reasonable prediction accuracy, it is clear that the model can be further enhanced by refining
data preprocessing, feature selection, and incorporating additional influential variables that
might be relevant to price determination, such as car condition, geographic location, and
historical pricing trends.

Future Work

For future improvements, several steps can be undertaken. First, expanding the dataset to
include a wider variety of car types, ages, and conditions can lead to a more generalized
model. Second, exploring more sophisticated machine learning techniques, such as deep
learning or ensemble methods, might help improve prediction accuracy by capturing more
complex relationships within the data. Third, incorporating real-time market data to account
for fluctuations in car prices due to demand, seasonality, or regional variations could make
the model more dynamic. Finally, the development of a user-friendly application that
integrates this model could allow consumers to access real-time car price estimates,
potentially with personalized recommendations based on their preferences and needs

10
 REFERENCES

1. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical
learning: With applications in R. Springer.
2. Kuhn, M., & Johnson, K. (2013). Applied predictive modeling. Springer.
3. Wickham, H. (2016). ggplot2: Elegant graphics for data analysis. Springer.
4. R Core Team. (2022). R: A language and environment for statistical computing. R
Foundation for Statistical Computing. https://www.R-project.org/
5. Kuhn, M. (2022). caret: Classification and regression training (R package version 6.0-
90). https://CRAN.R-project.org/package=caret
6. Zeileis, A., & Grothendieck, G. (2005). zoo: S3 infrastructure for regular and irregular
time series. Journal of Statistical Software, 14(6), 1–27. https://www.jstatsoft.org/v14/i06/
7. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2022). ISLR: Data for an introduction
to statistical learning with applications in R (R package version 4.1.0). https://CRAN.R-
project.org/package=ISLR

11