This project is a robust Flight Price Prediction web application developed using Flask, HTML, CSS, and a trained Machine Learning model saved as flight_fare_prediction.pkl. The application predicts flight prices based on user inputs, delivering accurate and meaningful insights.
- Accurate Flight Price Prediction: Utilizes a well-trained machine learning model to provide reliable fare predictions.
- User-Friendly Interface: Developed with Flask, HTML, and CSS to ensure seamless user interaction.
- Scalable and Modular Design: Well-structured codebase for easy maintenance and scalability.
- Deployment-Ready: Can be easily hosted on any cloud platform or local server.
├── app.py # Flask application code
├── flight_fare_prediction.pkl # Trained machine learning model
├── static # Static files (CSS, images, etc.)
├── templates # HTML templates (index.html)
├── README.md # Project documentation
- Backend: Flask (Python)
- Frontend: HTML, CSS
- Machine Learning Model:
flight_fare_prediction.pkl(Trained Model) - Deployment: Local server / Cloud Platforms
- Clone the repository:
git clone https://github.com/sagarprajapat2004/Flight-Price-Prediction.git- Navigate to the project directory:
cd Flight-Price-Prediction- Install required dependencies:
pip install -r requirements.txt- Run the Flask application:
python app.py- Open your browser and go to:
http://127.0.0.1:5000/
If you want to retrain the model, use the provided dataset and the model_training.py file. Ensure you have all necessary dependencies installed.
Dataset URL https://www.kaggle.com/datasets/nikhilmittal/flight-fare-prediction-mh/data
- Integrating Deep Learning Models for enhanced prediction accuracy.
- Deploying the application on AWS / Azure / Heroku.
- Building a more advanced and interactive frontend interface.
- Implementing Continuous Model Retraining with new datasets.