NexQuant/README.md

Predix

AI-powered Quantitative Trading Agent for EUR/USD Forex

Installation • Quick Start • Configuration • Features

---

Overview

Predix is an autonomous AI agent for quantitative trading strategies in the EUR/USD forex market. Built on a multi-agent framework, Predix automates the full research and development cycle:

• 📊 Data Analysis – Automatically analyzes market patterns and microstructure
• 💡 Strategy Discovery – Proposes novel trading factors and signals
• 🧠 Model Evolution – Iteratively improves predictive models
• 📈 Backtesting – Validates strategies on historical 1-minute data

Predix is optimized for 1-minute EUR/USD FX data (2020–2026) and uses Qlib as the underlying backtesting engine.

---

Installation

Prerequisites

• Python 3.10 or 3.11
• Docker (required for sandboxed code execution)
• Linux (officially supported; macOS/Windows may work with adjustments)

Quick Install

# Install from PyPI
pip install predix

# Or install from source
git clone https://github.com/PredixAI/predix
cd predix
pip install -e .

Development Setup

# Create conda environment
conda create -n predix python=3.10
conda activate predix

# Install in editable mode with dev dependencies
make dev

---

Quick Start

1. Health Check

Verify your environment is properly configured:

rdagent health_check --no-check-env

2. Configure LLM Backend

Create a .env file in your project root:

# Example: OpenAI configuration
cat << EOF > .env
CHAT_MODEL=gpt-4o
EMBEDDING_MODEL=text-embedding-3-small
OPENAI_API_BASE=https://api.openai.com/v1
OPENAI_API_KEY=your-api-key-here
EOF

Alternative providers:

• Azure OpenAI: Set AZURE_API_KEY, AZURE_API_BASE, AZURE_API_VERSION
• DeepSeek: Use CHAT_MODEL=deepseek/deepseek-chat with DEEPSEEK_API_KEY
• SiliconFlow (embedding): Use EMBEDDING_MODEL=litellm_proxy/BAAI/bge-m3

3. Run Quantitative Trading Loop

# Full factor & model co-evolution
rdagent fin_quant

# Factor-only evolution
rdagent fin_factor

# Model-only evolution
rdagent fin_model

4. Monitor Results

# Start the UI dashboard
rdagent ui --port 19899 --log-dir log/ --data-science

Then open http://127.0.0.1:19899 in your browser.

---

Configuration

Data Configuration

Edit data_config.yaml to customize:

instrument: EURUSD
frequency: 1min
data_path: ~/.qlib/qlib_data/eurusd_1min_data

# Walk-forward split
train_start: "2022-03-14"
train_end:   "2024-06-30"
valid_start: "2024-07-01"
valid_end:   "2024-12-31"
test_start:  "2025-01-01"
test_end:    "2026-03-20"

# Market context for LLM prompts
market_context:
  spread_bps: 1.5
  target_arr: 9.62          # Target annual return (%)
  max_drawdown: 20          # Max drawdown (%)

Environment Variables

Variable	Description	Example
CHAT_MODEL	LLM for reasoning	gpt-4o, deepseek-chat
EMBEDDING_MODEL	Embedding model	text-embedding-3-small
OPENAI_API_KEY	API key for OpenAI	sk-...
DEEPSEEK_API_KEY	API key for DeepSeek	sk-...
DS_LOCAL_DATA_PATH	Local data directory	./data

---

Features

🔄 Iterative Factor Evolution

Predix continuously proposes, implements, and validates new alpha factors:

• Learns from backtest feedback
• Avoids overfitting through walk-forward validation
• Discovers non-obvious patterns in order flow, volatility, and session dynamics

🧠 Model Architecture Search

Automatically explores and refines predictive models:

• Linear baselines (LightGBM, XGBoost)
• Deep learning (LSTM, Transformer, Temporal CNN)
• Ensemble methods

📚 Knowledge Base

Built-in knowledge accumulation across loops:

• Successful factors are archived
• Failed attempts inform future proposals
• Cross-loop learning improves robustness

🖥️ Interactive UI

Real-time dashboard for monitoring:

• Factor performance metrics
• Model architecture evolution
• Cumulative returns and drawdowns
• Code diffs and implementation history

---

Project Structure

predix/
├── rdagent/                 # Core agent framework
│   ├── app/                 # CLI and scenario apps
│   ├── components/          # Reusable agent components
│   ├── core/                # Core abstractions
│   ├── scenarios/           # Domain-specific scenarios
│   └── utils/               # Utilities
├── constraints/             # Constraint definitions
├── docs/                    # Documentation
├── web/                     # Web UI frontend
├── data_config.yaml         # Data configuration
├── pyproject.toml           # Project metadata
└── requirements.txt         # Dependencies

---

Data Setup

Predix uses 1-minute EUR/USD data. To prepare your dataset:

# Run the data setup script (if provided)
./setup_predix_eurusd.sh

# Or manually place data in:
# ~/.qlib/qlib_data/eurusd_1min_data/

Expected data columns: $open, $close, $high, $low, $volume

---

CLI Commands

Command	Description
rdagent fin_quant	Full factor & model co-evolution
rdagent fin_factor	Factor-only evolution
rdagent fin_model	Model-only evolution
rdagent fin_factor_report --report-folder=<path>	Extract factors from financial reports
rdagent general_model <paper-url>	Extract model from research paper
rdagent data_science --competition <name>	Kaggle/data science competition mode
rdagent ui --port 19899 --log-dir <path>	Start monitoring dashboard
rdagent health_check	Validate environment setup

---

Requirements

Core dependencies (see requirements.txt for full list):

• LLM: openai, litellm
• Data: pandas, numpy, pyarrow
• ML: scikit-learn, lightgbm, xgboost
• Backtesting: qlib (via Docker)
• UI: streamlit, plotly, flask

---

License

This project is licensed under the MIT License – see the LICENSE file for details.

---

Contributing

Contributions are welcome! Please:

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

For major changes, please open an issue first to discuss your approach.

---

Citation

If you use Predix in your research, please cite the underlying framework:

@misc{yang2025rdagentllmagentframeworkautonomous,
  title={R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science},
  author={Yang, Xu and Yang, Xiao and Fang, Shikai and Zhang, Yifei and Wang, Jian and Xian, Bowen and Li, Qizheng and Li, Jingyuan and Xu, Minrui and Li, Yuante and others},
  year={2025},
  eprint={2505.14738},
  archivePrefix={arXiv},
  primaryClass={cs.AI}
}

---

Support

• Issues: GitHub Issues
• Documentation: Read the Docs

---

Disclaimer

Predix is provided "as is" for research and educational purposes only. It is not intended for:

• Live trading or financial advice
• Production use without thorough testing
• Replacement of qualified financial professionals

Users assume all liability and should comply with applicable laws and regulations in their jurisdiction. Past performance does not guarantee future results.