🚗 AI Car Maintenance Predictor

Predict maintenance costs and component failure risks for cars using machine learning and real-world data.

� Live Demo: Try the Dashboard (Deploy to get this link)

✨ Features

• 🚗 40+ Car Models: Including luxury (BMW, Audi, Mercedes) and electric vehicles
• 🤖 ML Predictions: RandomForest models for cost prediction and failure classification
• 📊 Interactive Dashboard: Streamlit web interface with real-time predictions
• 🔄 Car Comparison: Compare maintenance costs between different vehicles
• ⛽ 6 Fuel Types: Petrol, Diesel, CNG, Electric, Hybrid, LPG
• 🧠 Smart Recommendations: AI-powered maintenance advice based on usage patterns

📁 Project Structure

AI_Car_Maintenance_Predictor/
├── data/
│   ├── raw/             # Raw scraped data
│   └── processed/       # Cleaned and feature-engineered data
├── src/
│   ├── scraper.py       # Web scraping scripts
│   ├── preprocess.py    # Data cleaning and feature engineering
│   ├── train_model.py   # ML training (regression/classification)
│   └── utils.py         # Helper functions
├── app/
│   └── dashboard.py     # Streamlit dashboard
├── requirements.txt     # Python dependencies
└── README.md

🛠️ Setup

1. Install dependencies:

   pip install -r requirements.txt

2. Run the data pipeline:

   # Step 1: Scrape data (optional - sample data included)
   python src/scraper.py
   
   # Step 2: Preprocess data
   python src/preprocess.py
   
   # Step 3: Train models
   python src/train_model.py

3. Launch dashboard:

   streamlit run app/dashboard.py

📊 Usage

Data Pipeline

1. Scraping: Collect car maintenance discussions from forums
2. Preprocessing: Clean data and engineer features
3. Training: Build ML models for cost and failure prediction
4. Prediction: Use dashboard for interactive predictions

Dashboard Features

• Input car details (model, mileage, age, fuel type)
• Get maintenance cost predictions
• View component failure risk analysis
• Explore data visualizations

🧠 ML Models

• Cost Prediction: RandomForestRegressor for maintenance cost estimation
• Failure Classification: RandomForestClassifier for component failure risk
• Features: Mileage, age, fuel type, usage patterns, service history

🎯 Key Metrics

• Cost Prediction: Mean Absolute Error (MAE), R² Score
• Failure Prediction: Accuracy, Precision, Recall, F1-Score

📈 Future Enhancements

• More data sources (manufacturer websites, service centers)
• Advanced ML models (XGBoost, Neural Networks)
• Real-time data updates
• Mobile app interface
• AI-powered insights with LangChain + OpenAI

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Submit a pull request

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📊 Model Performance

• Cost Prediction: MAE ₹1,660 | R² Score 0.822 (82% accuracy)
• Failure Classification: 100% accuracy on test data
• Cross Validation: R² Score 0.624 ± 0.569

🌟 Screenshots

Dashboard Interface

![Dashboard]

📄 License

This project is open source and available under the MIT License.

👨‍💻 Author

Jason William

• GitHub: @Jasonwill2004
• Project Link: AI Car Maintenance Predictor

---

⭐ Don't forget to give this project a star if you found it helpful!

Built with ❤️ using Python, Scikit-learn, and Streamlit