A simple yet effective machine learning web app that predicts the resale price of used cars based on user input like brand, model, fuel type, kilometers driven, and more. This project combines data preprocessing, regression modeling, and a user-friendly Flask web interface to deliver instant car price predictions.

• 📌 Brief Description
• 🚀 Live Demo
• 🧰 Tech Stack
• 🗃️ Project Structure
• 📈 Dataset Info
• ⚙️ How to Run Locally
• 🔍 Model Performance
• 🖼️ Screenshots
• 📄 License
• 🙌 Acknowledgements
• 👨‍💻 Author

This project aims to estimate the resale price of a used car using a machine learning model trained on real-world data scraped from Quikr.com. The application is built with Python, Flask, and scikit-learn, and it is deployed online for quick access. Users can select the car brand, model, fuel type, and enter usage details to receive an estimated selling price.

• 🔗 Website: Car Price Predictor (Heroku)
• ▶️ Demo Video: YouTube

• Frontend: HTML, CSS (Bootstrap)
• Backend: Python, Flask
• ML Model: Linear Regression (scikit-learn)
• Deployment: Heroku

car_price_predictor/
├── application.py
├── requirements.txt
├── Procfile
├── LinearRegressionModel.pkl
├── quikr_car.csv
├── Cleaned_Car_data.csv
├── Quikr Analysis.ipynb
├── templates/
│   └── index.html
├── static/
│   └── css/
│       └── style.css
├── demo.png
├── predict.png
└── README.md

Source: Scraped from Quikr.com

1. Clone the repository

git clone https://github.com/Akshay8087/car_price_predictor.git
cd car_price_predictor

2. Install dependencies

pip install -r requirements.txt\

3. Run the Flask app

python application.py

4. Open in browser

Visit: http://127.0.0.1:5000/

Model: Linear Regression
R² Score: 0.92 (on test data)
Notebook: All model training and evaluation steps are available in [Quikr Analysis.ipynb](Quikr Analysis.ipynb)