This system detects ICT patterns (Fair Value Gaps, Order Blocks, Liquidity Sweeps) during the London session (3:00-4:00 AM EST) and uses machine learning to grade pattern quality and predict trade outcomes.

Features

Pattern Detection: Automated detection of FVG, Order Blocks, and Liquidity patterns
Machine Learning: ML models for pattern grading and setup classification
Labeling System: Integrated labeling workflow for training data
Backtesting: Comprehensive backtesting framework
Alert System: Real-time alerts via Telegram/Slack
Production Ready: Comprehensive logging, error handling, and monitoring

Project Structure

ict-ml-trading/
├── src/              # Source code
├── config/           # Configuration files
├── data/             # Data storage
├── models/           # Trained ML models
├── logs/             # Application logs
├── tests/            # Test suite
├── scripts/          # Utility scripts
└── docs/             # Documentation

Quick Start

Prerequisites

Python 3.10+
PostgreSQL (optional, for production)

Installation

Clone the repository:

git clone <repository-url>
cd ict-ml-trading

Create virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

Install dependencies:

make install-dev

Set up environment variables:

cp .env.example .env
# Edit .env with your configuration

Initialize database (optional):

make setup-db

Development

Running Tests

make test

Code Formatting

make format

Linting

make lint

Type Checking

make type-check

Configuration

Configuration files are located in config/:

config.yaml - Main application configuration
logging.yaml - Logging setup
detectors.yaml - Pattern detector parameters
models.yaml - ML model hyperparameters
trading.yaml - Trading strategy parameters
alerts.yaml - Alert system configuration
database.yaml - Database connection settings

Version History

See CHANGELOG.md for detailed version history.

License

MIT License

Contributing

See docs/contributing.md for contribution guidelines.