1. Abstract

The automobile market has seen a significant rise in the buying and selling of used cars. Determining the correct selling price of a used car is often difficult due to various influencing factors such as car age, fuel type, mileage, brand, and present market demand. Accurate price estimation is important for both sellers and buyers in the used car market.

This project focuses on predicting the selling price of used cars using Machine Learning techniques. The dataset used in this project contains information about different car attributes such as present price, kilometers driven, fuel type, transmission type, number of owners, and year of purchase. These attributes help in determining the resale value of the car.

In this project, a Random Forest Regressor model is used to build the prediction system. Data preprocessing techniques such as handling missing values, encoding categorical variables, and feature extraction are applied to prepare the dataset for model training. The trained model learns relationships between car features and their selling prices.

Finally, the trained model is deployed using a Django-based web application, allowing users to input car details and obtain predicted selling prices. This project demonstrates how machine learning can be applied to solve real-world problems in the automobile resale market.

2. Objectives

The main objectives of this project are:

1. To understand the problem of predicting used car prices using machine learning.
2. To study the factors affecting the selling price of used cars.
3. To analyse historical car selling data and identify important features.
4. To preprocess and prepare data for machine learning algorithms.
5. To understand regression algorithms used for price prediction.
6. To implement a Random Forest Regressor model for car price prediction.
7. To evaluate the performance of the prediction model.
8. To deploy the trained model using a Django-based web application.

3. Existing System

In the existing system, the selling price of used cars is usually estimated based on:

1. Manual price estimation by dealers
2. Personal experience of sellers
3. Market demand and negotiation
4. Basic statistical analysis

Limitations of Existing Systems

1. Price estimation depends heavily on human judgement.
2. Manual analysis of multiple car features is time-consuming.
3. Difficult to analyse large datasets of car sales.
4. Traditional methods may produce inaccurate predictions.
5. Lack of automated systems for real-time car price prediction.

These limitations highlight the need for an intelligent machine learning-based system.

4. Proposed System

The proposed system predicts the selling price of used cars using Machine Learning algorithms, specifically the Random Forest Regressor model.

In this system:

1. Historical used car data is collected from a dataset.
2. Data preprocessing is performed to clean and prepare the dataset.
3. Important features influencing car prices are identified.
4. A Random Forest regression model is trained using the dataset.
5. The model learns patterns between car features and their selling prices.
6. The trained model predicts the price of a car based on its features.
7. The prediction model is deployed using a Django web application.

This system provides a data-driven and automated approach to estimate used car prices.

5. Implementation Procedure

The implementation of this project includes the following steps:

Step 1: Data Collection

The dataset containing information about used cars is collected. It includes attributes such as:

1. Car name
2. Year of purchase
3. Present price
4. Kilometers driven
5. Fuel type
6. Transmission type
7. Number of previous owners
8. Selling price

Step 2: Data Preprocessing

The dataset is processed by:

1. Handling missing or inconsistent values
2. Encoding categorical variables (fuel type, transmission)
3. Feature extraction such as calculating car age
4. Normalizing or scaling numerical data

Step 3: Exploratory Data Analysis (EDA)

1. Visualization of relationships between features and price
2. Identification of important influencing factors
3. Analysis of distribution of car prices

Step 4: Feature Selection

1. Selecting the most relevant features for prediction
2. Removing unnecessary or redundant attributes

Step 5: Model Development

A Random Forest Regressor model is developed including:

1. Training dataset preparation
2. Model training using car features
3. Learning patterns between car attributes and selling prices

Step 6: Model Evaluation

The model performance is evaluated using metrics such as:

1. Mean Squared Error (MSE)
2. Root Mean Squared Error (RMSE)
3. R² Score (Coefficient of Determination)

Step 7: Model Deployment

1. The trained model is integrated into a Django framework
2. A web interface is developed
3. Users enter car details
4. The system predicts and displays the estimated selling price

6. Software Requirements

The software tools used in this project include:

1. Python – Programming language
2. Jupyter Notebook / Google Colab – Development environment
3. Django – Web framework for deployment
4. NumPy – Numerical computation
5. Pandas – Data manipulation and analysis
6. Matplotlib / Seaborn – Data visualization
7. Scikit-learn – Machine learning algorithms
8. Pickle / Joblib – Model saving and loading
9. GitHub – Version control
10. Heroku – Web application deployment platform

7. Hardware Requirements

Minimum Hardware Requirements:

1. Processor: Intel i5 or higher
2. RAM: 8 GB or higher
3. Storage: 256 GB or higher
4. Laptop or Desktop Computer
5. Internet connection for dataset access and deployment

8. Advantages of the Project

1. Provides accurate prediction of used car selling prices.
2. Reduces human effort in price estimation.
3. Helps buyers and sellers determine fair market value.
4. Handles multiple car features simultaneously.
5. Provides faster and automated predictions.
6. Deployable as a web application for real-time usage.
7. Demonstrates practical application of machine learning in the automobile market.