# QuantaAlpha **Repository Path**: jasonlp/QuantaAlpha ## Basic Information - **Project Name**: QuantaAlpha - **Description**: No description available - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2026-08-16 - **Last Updated**: 2026-08-16 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README
QuantaAlpha Framework Overview

๐ŸŒŸ QuantaAlpha: LLM-Driven Self-Evolving Framework for Factor Mining

๐Ÿงฌ Achieving superior quantitative alpha through trajectory-based self-evolution with diversified planning initialization, trajectory-level evolution, and structured hypothesis-code constraint

๐ŸŒ English | ไธญๆ–‡

Quick Start Web Dashboard User Guide QuantaAlpha-claw
--- ## ๐Ÿ”ญ Coming Soon๏ผš[QuantaAlpha-claw](https://github.com/QuantaAlpha/QuantaAlpha-claw) (Agent-Native Alpha Research) We are building **[QuantaAlpha-claw](https://github.com/QuantaAlpha/QuantaAlpha-claw)**, the next research harness for QuantaAlpha. It extends the current self-evolving factor-mining framework toward a swarm-style, agent-native research system: Lead / Reviewer / Miner agents explore in parallel, coordinate through session memory, and evolve factors through skill-based operators with auditable lineage and stricter Walk-Forward validation. `Swarm-style agent co-evolution` ยท `Skill-driven research loop` ยท `Persistent factor memory` ยท `Lineage-aware factor evolution` Explore the next work: **https://github.com/QuantaAlpha/QuantaAlpha-claw** --- ## ๐ŸŽฏ Overview **QuantaAlpha** transforms how you discover quantitative alpha factors by combining LLM intelligence with evolutionary strategies. Just describe your research direction, and watch as factors are automatically mined, evolved, and validated through self-evolving trajectories.

๐Ÿ’ฌ Research Direction โ†’ ๐Ÿงฉ Diversified Planning โ†’ ๐Ÿ”„ Trajectory โ†’ โœ… Validated Alpha Factors

**Demo**: Below is a short demo of the full flow from research direction to factor mining and backtesting UI.

โ–ถ Click to play the QuantaAlpha end-to-end workflow demo.

--- ## ๐Ÿ“Š Performance ### 1. Zero-Shot Cross-Market Transfer
Zero-Shot Transfer

Factors mined on CSI 300, transferred zero-shot to CSI 500 and S&P 500 (cumulative return). By the end of the test period, QuantaAlpha reaches ~40.3% cumulative excess return on CSI 500 and ~19.1% on S&P 500.

### 2. Main Results on CSI 300
| Dimension | Metric | Performance | | :---: | :---: | :---: | | **Predictive Power** | Information Coefficient (IC) | **0.0472** | | | Rank IC | **0.0459** | | **Strategy Performance** | Annualized Return (ARR) | **4.68%** | | | Information Ratio (IR) | **0.6453** | | | Max Drawdown (MDD) | **11.80%** |

Best configuration (QuantaAlpha + GPT-5.2) on CSI 300, test period 2022โ€“2025. Full comparison against classical machine-learning, deep-learning, factor-library, and LLM-agent baselines below.

Main Experiment Results
### 3. Robustness & Mining Efficiency
Annual IC and Rank IC

Annual IC and Rank IC on CSI 300 (2022โ€“2025): QuantaAlpha stays robust through the 2023 market regime shift, where baselines collapse.

IC Evolution over Iterations

IC evolution over the first five mining iterations: QuantaAlpha maintains the highest IC throughout.

--- ## ๐Ÿš€ Quick Start ### 1. Clone & Install ```bash git clone https://github.com/QuantaAlpha/QuantaAlpha.git cd QuantaAlpha conda create -n quantaalpha python=3.10 conda activate quantaalpha # Install the package in development mode SETUPTOOLS_SCM_PRETEND_VERSION=0.1.0 pip install -e . # Install additional dependencies pip install -r requirements.txt ``` ### 2. Configure Environment ```bash cp configs/.env.example .env ``` Edit `.env` with your settings: ```bash # === Required: Data Paths === QLIB_DATA_DIR=/path/to/your/qlib/cn_data # Qlib data directory DATA_RESULTS_DIR=/path/to/your/results # Output directory # === Required: LLM API === OPENAI_API_KEY=your-api-key OPENAI_BASE_URL=https://your-llm-provider/v1 # e.g. DashScope, OpenAI CHAT_MODEL=deepseek-v3 # or gpt-4, qwen-max, etc. REASONING_MODEL=deepseek-v3 ``` ### 3. Prepare Data QuantaAlpha requires two types of data: **Qlib market data** (for backtesting) and **pre-computed price-volume HDF5 files** (for factor mining). We provide all of them on HuggingFace for convenience. > **Dataset**: [https://huggingface.co/datasets/QuantaAlpha/qlib_csi300](https://huggingface.co/datasets/QuantaAlpha/qlib_csi300) | File | Description | Size | Usage | | :--- | :--- | :--- | :--- | | `cn_data.zip` | Qlib raw market data (A-share, 2016โ€“2025) | 493 MB | Required for Qlib initialization & backtesting | | `daily_pv.h5` | Pre-computed full price-volume data | 398 MB | Required for factor mining | | `daily_pv_debug.h5` | Pre-computed debug subset (smaller) | 1.41 MB | Required for factor mining (debug/validation) | > **Why provide HDF5 files?** The system can auto-generate `daily_pv.h5` from Qlib data on first run, but this process is very slow. Downloading pre-built HDF5 files saves significant time. #### Step 1: Download ```bash # Option A: Using huggingface-cli (recommended) pip install huggingface_hub huggingface-cli download QuantaAlpha/qlib_csi300 --repo-type dataset --local-dir ./hf_data # Option B: Using wget mkdir -p hf_data wget -P hf_data https://huggingface.co/datasets/QuantaAlpha/qlib_csi300/resolve/main/cn_data.zip wget -P hf_data https://huggingface.co/datasets/QuantaAlpha/qlib_csi300/resolve/main/daily_pv.h5 wget -P hf_data https://huggingface.co/datasets/QuantaAlpha/qlib_csi300/resolve/main/daily_pv_debug.h5 ``` #### Step 2: Extract & Place Files ```bash # 1. Extract Qlib data unzip hf_data/cn_data.zip -d ./data/qlib # 2. Place HDF5 files into the default data directories mkdir -p git_ignore_folder/factor_implementation_source_data mkdir -p git_ignore_folder/factor_implementation_source_data_debug cp hf_data/daily_pv.h5 git_ignore_folder/factor_implementation_source_data/daily_pv.h5 cp hf_data/daily_pv_debug.h5 git_ignore_folder/factor_implementation_source_data_debug/daily_pv.h5 ``` > **Note**: `daily_pv_debug.h5` must be renamed to `daily_pv.h5` when placed in the debug directory. #### Step 3: Configure Paths in `.env` ```bash # Point to the extracted Qlib data directory (must contain calendars/, features/, instruments/) QLIB_DATA_DIR=./data/qlib/cn_data # Output directory for experiment results DATA_RESULTS_DIR=./data/results ``` The HDF5 data directories can also be customized via environment variables if you prefer a different location: ```bash # Optional: override default HDF5 data paths FACTOR_CoSTEER_DATA_FOLDER=/your/custom/path/factor_source_data FACTOR_CoSTEER_DATA_FOLDER_DEBUG=/your/custom/path/factor_source_data_debug ``` ### 4. Run Factor Mining ```bash ./run.sh "" # Example: Run with a research direction ./run.sh "Price-Volume Factor Mining" # Example: Run with custom factor library suffix ./run.sh "Microstructure Factors" "exp_micro" ``` The experiment will automatically mine, evolve, and validate alpha factors, and save all discovered factors to `all_factors_library*.json`. ### 5. Independent Backtesting After mining, combine factors from the library for a full-period backtest: ```bash # Backtest with custom factors only python -m quantaalpha.backtest.run_backtest \ -c configs/backtest.yaml \ --factor-source custom \ --factor-json all_factors_library.json # Combine with Alpha158(20) baseline factors python -m quantaalpha.backtest.run_backtest \ -c configs/backtest.yaml \ --factor-source combined \ --factor-json all_factors_library.json # Dry run (load factors only, skip backtest) python -m quantaalpha.backtest.run_backtest \ -c configs/backtest.yaml \ --factor-source custom \ --factor-json all_factors_library.json \ --dry-run -v ``` Results are saved to the directory specified in `configs/backtest.yaml` (`experiment.output_dir`). > ๐Ÿ“˜ Need help? Check our comprehensive **[User Guide](docs/user_guide.md)** for advanced configuration, experiment reproduction, and detailed usage examples. --- ## ๐Ÿ–ฅ๏ธ Web UI QuantaAlpha provides a web-based dashboard where you can complete the entire workflow through a visual interface โ€” no command line needed. ```bash conda activate quantaalpha cd frontend-v2 bash start.sh # Visit http://localhost:3000 ``` - **โš™๏ธ Settings**: Configure LLM API, data paths, and experiment parameters directly in the UI - **โ›๏ธ Factor Mining**: Start experiments with natural language input and monitor progress in real-time - **๐Ÿ“š Factor Library**: Browse, search, and filter all discovered factors with quality classifications - **๐Ÿ“ˆ Independent Backtest**: Select a factor library and run full-period backtests with visual results --- ## ๐Ÿ’ฌ User Community
| WeChat Group | | :---: | | WeChat Group |
--- ## ๐Ÿค Contributing We welcome all forms of contributions to make QuantaAlpha better! Here's how you can get involved: - **๐Ÿ› Bug Reports**: Found a bug? [Open an issue](https://github.com/QuantaAlpha/QuantaAlpha/issues) to help us fix it. - **๐Ÿ’ก Feature Requests**: Have a great idea? [Start a discussion](https://github.com/QuantaAlpha/QuantaAlpha/discussions) to suggest new features. - **๐Ÿ“ Docs & Tutorials**: Improve documentation, add usage examples, or write tutorials. - **๐Ÿ”ง Code Contributions**: Submit PRs for bug fixes, performance improvements, or new functionality. - **๐Ÿงฌ New Factors**: Share high-quality factors discovered in your own runs to benefit the community. --- ## ๐Ÿ™ Acknowledgments Special thanks to: - [Qlib](https://github.com/microsoft/qlib) - Quantitative investment platform by Microsoft - [RD-Agent](https://github.com/microsoft/RD-Agent) - An automated R&D framework by Microsoft (NeurIPS 2025) - [AlphaAgent](https://github.com/RndmVariableQ/AlphaAgent) - Multi-agent alpha factor mining framework (KDD 2025) --- ## ๐ŸŒ About QuantaAlpha - QuantaAlpha was founded in **April 2025** by a team of professors, postdocs, PhDs, and master's students from **Tsinghua University, Peking University, CAS, CMU, HKUST**, and more. ๐ŸŒŸ Our mission is to explore the **"quantum"** of intelligence and pioneer the **"alpha"** frontier of agent research โ€” from **CodeAgents** to **self-evolving intelligence**, and further to **financial and cross-domain specialized agents**, we are committed to redefining the boundaries of AI. โœจ In **2026**, we will continue to produce high-quality research in the following directions: - **CodeAgent**: End-to-end autonomous execution of real-world tasks - **DeepResearch**: Deep reasoning and retrieval-augmented intelligence - **Agentic Reasoning / Agentic RL**: Agent-based reasoning and reinforcement learning - **Self-evolution and collaborative learning**: Evolution and coordination of multi-agent systems ๐Ÿ“ข We welcome students and researchers interested in these directions to join us! ๐Ÿ”— **Team Homepage**: [QuantaAlpha](https://quantaalpha.github.io/) ๐Ÿ“ง **Email**: quantaalpha.ai@gmail.com ## ๐ŸŒ About AIFin Lab Initiated by Professor Liwen Zhang from Shanghai University of Finance and Economics (SUFE), **AIFin Lab** is deeply rooted in the interdisciplinary fields of **AI + Finance, Statistics, and Data Science**. The team brings together cutting-edge scholars from top institutions such as SUFE, FDU, SEU, CMU, and CUHK. We are dedicated to building a comprehensive "full-link" system covering data, models, benchmarks, and intelligent prompting. ๐Ÿ“ข We are actively looking for talented students (UG/Master/PhD) and researchers worldwide who are passionate about AI Agent security and financial intelligence to join **AIFin Lab**! ๐Ÿ“ง **Email**: [aifinlab.sufe@gmail.com](mailto:aifinlab.sufe@gmail.com) (please CC to [zhang.liwen@shufe.edu.cn](mailto:zhang.liwen@shufe.edu.cn)) We look forward to hearing from you! --- ## ๐Ÿ“– Citation If you find QuantaAlpha useful in your research, please cite our work: ```bibtex @misc{han2026quantaalphaevolutionaryframeworkllmdriven, title={QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining}, author={Jun Han and Shuo Zhang and Wei Li and Zhi Yang and Yifan Dong and Tu Hu and Jialuo Yuan and Xiaomin Yu and Yumo Zhu and Fangqi Lou and Xin Guo and Zhaowei Liu and Tianyi Jiang and Ruichuan An and Jingping Liu and Biao Wu and Rongze Chen and Kunyi Wang and Yifan Wang and Sen Hu and Xinbing Kong and Liwen Zhang and Ronghao Chen and Huacan Wang}, year={2026}, eprint={2602.07085}, archivePrefix={arXiv}, primaryClass={q-fin.ST}, url={https://arxiv.org/abs/2602.07085}, } ``` --- ## โญ Star History [![Star History Chart](https://api.star-history.com/svg?repos=QuantaAlpha/QuantaAlpha&type=date&legend=top-left)](https://www.star-history.com/#QuantaAlpha/QuantaAlpha&type=date&legend=top-left) ---
**โญ If QuantaAlpha helps you, please give us a star!** Made with โค๏ธ by the QuantaAlpha Team