CarValue AI is a sophisticated end-to-end machine learning application designed to provide instantaneous and highly accurate resale valuations for used vehicles. Built with a focus on Premium Dark-Mode UI/UX, Robust JWT Authentication, and Real-Time ML Inference, it empowers buyers and sellers with data-backed insights before they enter negotiations.
| Feature | Description |
|---|---|
| 🤖 AI Valuation | Random Forest Regressor calibrated on real-world datasets for hyper-accurate price estimation. |
| 🔐 Secure Auth | Full JWT-based authentication flow with protected user dashboards and sessions. |
| 📊 Prediction History | Track and manage all your past valuations in a dedicated activity feed. |
| 💬 AI Copilot | Integrated valuation assistant grounded in dataset statistics to guide your pricing strategy. |
| ✨ Micro-Animations | Framer Motion powered transitions and glow effects for a high-end tactile experience. |
- R² Score:
0.9762(Explains 97.6% of price variance) - Mean Absolute Error (MAE):
$370.67 - Algorithm: Random Forest Regressor (100 Estimators)
- Features: Brand, Model, Year, Mileage, Engine Size, Fuel Type, Transmission, Doors, Owner Count.
- Preprocessing: Label encoding for categorical variables and feature scaling.
- Training: Optimized using Scikit-Learn with a 80/20 train-test split.
- Inference: FastAPI backend serves the
.pklmodel artifacts with sub-50ms latency.
- Framework: React 18 + Vite
- Styling: Vanilla CSS3 + Modern Design Tokens (Glassmorphism)
- Animations: Framer Motion
- Icons: Lucide React
- Runtime: Python 3.10
- Framework: FastAPI (Asynchronous API)
- Security: OAuth2 with Password Hashing (Passlib)
- Database: SQLite with SQLAlchemy ORM
| Folder | Description |
|---|---|
frontend/ |
React source code, components, and production build config. |
backend/ |
FastAPI server, auth modules, and database models. |
ml/ |
Training scripts, data pipeline, and exported model artifacts. |
data/ |
Source dataset (car_data.csv) used for retraining. |
git clone https://github.com/PrudhviRaavi/CarValue-AI.git
cd CarValue-AIcd backend
python -m venv venv
# Activate venv: .\venv\Scripts\activate (Windows) OR source venv/bin/activate (macOS)
pip install -r requirements.txt
uvicorn main:app --reloadcd frontend
npm install
npm run devContributions are welcome! If you have a suggestion that would make this better, please fork the repo and create a pull request.
👉 Read the full Contributing Guide →
This project is licensed under the MIT License — see the docs/LICENSE file for details.
Developed by Prudhvi Raavi | GitHub
Disclaimer: CarValue AI provides estimates based on historical data. Market fluctuations and vehicle condition may affect actual resale value.