✨ Key Features

🏗️ Project Structure

StockMarketPrediction/
│
├── app.py                          # Application factory — wires everything together
├── run.py                          # Entry point to start the server
├── run_adaptive_monitor.py         # Background adaptive ML monitoring service
├── models.py                       # SQLAlchemy DB models (User, Stock, Prediction, Alert...)
├── config.py                       # App configuration (dev / prod)
├── configure_email.py              # Email setup utility
├── requirements.txt                # Python dependencies
│
├── routes/                         # Flask Blueprints
│   ├── auth.py                     # /auth — Login, register, OTP, password reset
│   ├── user.py                     # /user — Home, watchlist, notifications
│   ├── admin.py                    # /admin — Dashboard, stock & user management
│   └── api.py                      # /api  — JSON endpoints for charts & predictions
│
├── services/                       # Business logic layer
│
├── ml_models/
│   └── adaptive/                   # Adaptive self-improving ML models
│
├── utils/
│   ├── email_service.py            # Flask-Mail wrapper
│   ├── gemini_ai.py                # Google Gemini AI client
│   └── scheduler.py                # Background job scheduler
│
├── templates/                      # Jinja2 HTML templates
│   └── errors/                     # 404 / 500 error pages
│
├── static/                         # CSS, JS, images
├── data/                           # Raw & processed stock data
├── uploads/                        # User-uploaded files
└── .gitignore

🗄️ Database Models

The app uses Flask-SQLAlchemy with these core models:

⚡ Getting Started

Prerequisites

• Python 3.10+
• pip
• A Gmail (or SMTP) account for email features
• Google Gemini API key (optional but recommended)

1 · Clone the Repository

bash
git clone https://github.com/ganesha-raut/StockMarketPrediction.git
cd StockMarketPrediction

2 · Create Virtual Environment

bash
python -m venv venv

# macOS / Linux
source venv/bin/activate

# Windows
venv\Scripts\activate

3 · Install Dependencies

bash
pip install -r requirements.txt

4 · Configure the App

Edit config.py and set:

python
SECRET_KEY        = 'your-secret-key'
GEMINI_API_KEY    = 'your-gemini-api-key'   # optional
MAIL_USERNAME     = 'your@gmail.com'
MAIL_PASSWORD     = 'your-app-password'

5 · Run the Server

bash
python run.py

🟢 App live at http://127.0.0.1:5000
🔑 Default admin: admin@stockai.com / admin123 (change immediately!)

6 · Start the Adaptive Monitor (optional)

bash
python run_adaptive_monitor.py

Runs the background ML monitoring service that re-evaluates prediction accuracy and retrains models automatically.

🤖 Machine Learning Pipeline

Raw yfinance Data
      │
      ▼
Feature Engineering
(SMA, EMA, RSI, MACD, Volume, Sentiment Score)
      │
      ▼
Adaptive ML Models  ──► Accuracy Tracker
(ml_models/adaptive/)        │
      │                  Auto-retrain if
      ▼                  accuracy drops
Prediction + Confidence
(trend: bullish / bearish / neutral)
      │
      ▼
Recommendation: BUY / SELL / HOLD  +  Smart Alerts

Pre-loaded Indian Stocks: TCS · RELIANCE · HDFCBANK · INFY · ICICIBANK · HINDUNILVR · ITC · SBIN · BHARTIARTL · WIPRO

🛣️ API Endpoints

🔔 Alert Types

🤝 Contributing

1. Fork the repo
2. Create your 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

📄 License

This project is open-source under the MIT License.