QuantGPT

Agent-Driven LLM Quant Research Engine — Autonomous Factor Mining at WorldQuant BRAIN Submission Quality

LLM Agent 自治因子挖矿 → 批量回测 → 多维评分 → 反过拟合验证 → WQ BRAIN 自动提交 | 全程零人工干预

Quick Start · Architecture · API Docs · MCP Guide · Factor Mining · Contributing

What Is QuantGPT

QuantGPT is an agent-driven factor research engine — not a backtest library, not a chatbot wrapper. It gives an LLM Agent (Claude, via MCP) a complete toolkit to autonomously discover, evaluate, iterate, and submit alpha factors to WorldQuant BRAIN, with zero human intervention per research cycle.

The core architecture:

LLM Agent (Claude Code / Claude Desktop)
    │
    ├── MCP Tools (14 个)         ← Agent 的工具箱
    │   ├── run_backtest           ← 全市场分组回测
    │   ├── score_factor           ← 0-100 综合评分
    │   ├── diagnose_factor        ← 失败模式诊断
    │   ├── run_anti_overfit       ← 4 项反过拟合检验
    │   ├── run_rolling_validation ← Walk-forward 验证
    │   ├── validate_expression    ← 语法校验
    │   ├── list_operators         ← 50+ 算子文档
    │   ├── list_universes         ← 股票池和基准
    │   ├── wq_brain_submit        ← WQ BRAIN 单因子提交
    │   ├── wq_brain_batch_submit  ← 批量参数扫描提交
    │   ├── wq_brain_submit_by_ids ← 按 ID 提交
    │   ├── wq_brain_list_alphas   ← 查询已提交 alpha
    │   ├── wq_brain_check_alphas  ← 检查 alpha 状态
    │   └── wq_brain_finalize_submissions ← 最终提交确认
    │
    ├── Evolution Engine           ← 因子进化引擎
    │   ├── MutationEngine (8 方向突变)
    │   ├── CrossoverEngine (高分因子交叉)
    │   ├── MetaEvolutionSelector (自适应策略)
    │   └── TrajectoryAnalyzer (轨迹分析)
    │
    ├── WQ BRAIN Integration       ← WorldQuant 直连
    │   ├── Dollar-neutral 模拟
    │   ├── IS 检测对齐
    │   ├── Fitness 评分
    │   └── 一键正式提交
    │
    └── Knowledge Base             ← 跨会话知识积累
        ├── rules/    (已验证规则)
        ├── findings/ (经验发现)
        └── failures/ (已证伪路径)

How It Differs from "AI Backtest Tools"

传统工具（包括 ChatGPT + 回测库）的模式是：人类想因子 → 工具跑回测 → 人类看结果。Agent 是执行者，人类是决策者。

QuantGPT 的模式是：人类定义目标 → Agent 自治研究 → 人类审阅产出。Agent 是研究者，人类是审阅者。

这不是接口层的区别（自然语言 vs. 代码），而是决策权的区别。Agent 自主决定：探索哪个方向、生成什么表达式、评估哪些指标、何时迭代、何时放弃、何时提交。

Production Track Record

Validated Results — Factors Submitted to BRAIN

QuantGPT Agent 已产出 3 个正式提交因子，全部通过 WQ BRAIN IS 检测：

3 个因子代表不同的 alpha 来源：Debt-Momentum 结合动量反转与基本面（债务/企业价值），行业中性化；VWAP Decay Reversal 捕捉价格偏离 VWAP 的衰减回归，市场中性化；Returns-Volume Momentum 捕捉收益率与相对成交量的衰减动量，市场中性化。全程 Agent 自治完成。

_{Debt-Momentum Composite — 已正式提交：Sharpe 1.77, Fitness 1.26, Returns 20.18%, IS 全部 PASS}

_{VWAP Decay Reversal — 已正式提交：Sharpe 1.69, Fitness 1.07, Returns 18.63%, IS 全部 PASS}

_{Returns-Volume Momentum — 已正式提交：Sharpe 1.60, Fitness 1.03, Returns 24.15%, IS 全部 PASS}

Autonomous Factor Mining — The Core Loop

This is QuantGPT's defining capability.

Agent 读知识库、设计假设、批量实验、分析结果、积累知识、自我迭代，每个结论经过双模型交叉验证。一个研究循环产出经过验证的、可提交 WQ BRAIN 的因子。

Research Cycle

                    ┌─────────────────────────────┐
                    │  Research Notes & Knowledge  │
                    │  (Rules / Findings / Fails)  │
                    └──────────┬──────────────────┘
                               │ read
                               ▼
┌──────────┐    ┌──────────────────────────┐    ┌──────────────────┐
│  Phase 0 │───▶│  Phase 1: Factor Design  │───▶│  Phase 2: Batch  │
│  Context │    │  Hypothesis → Expression │    │  Backtest (10-20 │
│  Loading │    │  1-3 candidates per idea │    │  concurrent)     │
└──────────┘    └──────────────────────────┘    └────────┬─────────┘
                                                         │
                               ┌─────────────────────────┘
                               ▼
                ┌──────────────────────────────────────────┐
                │  Phase 3: Four-Step Analysis             │
                │                                          │
                │  ① Fact Collection (metrics vs baseline) │
                │  ② Independent Judgment (Agent)          │
                │  ③ Cross-Review (DeepSeek Reasoner)      │
                │  ④ Consensus or Divergence Resolution    │
                └──────────────────┬───────────────────────┘
                                   │
                    ┌──────────────┴──────────────┐
                    ▼                             ▼
          ┌─────────────────┐          ┌──────────────────┐
          │  Phase 4: Update │          │  Phase 5: Stop?  │
          │  Notes + Knowledge│         │  Converged /     │
          │  Base             │◀────────│  Time / Rounds   │
          └─────────────────┘          └──────────────────┘
                    │                         │ no
                    │                         └──▶ back to Phase 1
                    ▼
          ┌──────────────────┐
          │  Phase 6: Report │
          │  A/B factors +   │
          │  new knowledge   │
          └──────────────────┘

Key Mechanisms

research_notes/knowledge/
├── rules/       ← 已验证的稳定规则（必须遵守）
├── findings/    ← 经验发现（参考）
└── failures/    ← 已证伪路径（禁止重复）

from scripts.factor_miner import batch_evaluate
results = batch_evaluate(
    server, expressions, params,
    max_concurrent=10
)

上面 Validated Results 中的因子就是这个流程的产出。 多轮迭代，3 个因子正式提交 WQ BRAIN（IS 全部通过）。完整方法论见 Factor Mining Guide。

Architecture

┌────────────────────────────────────────────────────────────────────┐
│                     QuantGPT Research Engine                       │
├─────────────┬──────────────────────────────┬───────────────────────┤
│             │         Core Engine          │                       │
│  Agent      │  ┌──────────────────────┐   │   Data Layer          │
│  Interface  │  │  Expression Parser   │   │  ┌─────────────────┐  │
│             │  │  50+ operators       │   │  │ baostock (free)  │  │
│ MCP Tools   │  │  WQ BRAIN compatible │   │  │ akshare (free)   │  │
│ REST API    │  └──────────┬───────────┘   │  │ PolarDB (opt)    │  │
│ Web UI      │  ┌──────────▼───────────┐   │  │ Parquet cache    │  │
│ (monitor)   │  │  Backtest Engine     │   │  └─────────────────┘  │
│             │  │  Rank-based grouping │   │                       │
│             │  │  WQ BRAIN aligned    │   │   AI Layer            │
│             │  └──────────┬───────────┘   │  ┌─────────────────┐  │
│             │  ┌──────────▼───────────┐   │  │ DeepSeek LLM    │  │
│             │  │  Validation Suite    │   │  │ Factor design   │  │
│             │  │  Anti-overfit (4x)   │   │  │ Cross-review    │  │
│             │  │  Walk-forward        │   │  │ Mutation engine │  │
│             │  │  WQ BRAIN simulation │   │  └─────────────────┘  │
│             │  └──────────────────────┘   │                       │
│             │                             │   Storage             │
│             │  Evolution Engine           │  ┌─────────────────┐  │
│             │  Trajectory → Meta-Evo →    │  │ SQLite (default)│  │
│             │  Mutation / Crossover       │  │ PostgreSQL (opt)│  │
│             │                             │  └─────────────────┘  │
├─────────────┴──────────────────────────────┴───────────────────────┤
│  Agent Orchestrator: Claude Code skill loop / Claude Desktop MCP   │
└────────────────────────────────────────────────────────────────────┘

Tech Stack

Key Engineering Decisions

1. Expression Parser — The Core Differentiator

自研的表达式解析器（expression_parser.py, 870+ lines）是整个系统的核心：

• 50+ 算子：截面（rank, zscore）、时序（ts_corr, decay_linear）、非线性（sign_power）、条件（where, trade_when）、技术指标（rsi, macd, atr）
• 双模式：mode="wq" 仅允许 WQ BRAIN 兼容算子（提交前校验），mode="local" 开放全部算子
• 语义正确的截面/时序分离：rank() 按 trade_date 分组（截面），ts_mean() 按 stock_code 分组（时序），自动处理分组逻辑
• 安全约束：递归深度限制、窗口上限、表达式长度限制，防止恶意输入

2. Three-Layer Anti-Overfit System

3. Evolutionary Factor Iteration

受 QuantaAlpha 启发的三阶段自动搜索：

TrajectoryAnalyzer → MetaEvolutionSelector → Strategy Execution
 (质量指标评估)       (EXPLOIT/EXPLORE/        (MutationEngine ×8 方向
                      RECOMBINE/SIMPLIFY)       / CrossoverEngine)

8 种定向突变：时间窗口变异、算子替换、复杂度调整、截面变换叠加等。5 维评分驱动迭代方向。

4. Agent-First Access Model

Competitive Landscape

Quick Start

Option 1: Agent Mode (Recommended)

git clone https://github.com/Miasyster/QuantGPT.git && cd QuantGPT
make setup   # creates venv, installs deps, generates .env
make run     # starts server at http://localhost:8003

Add MCP configuration to Claude Code or Claude Desktop:

{
  "mcpServers": {
    "quantgpt": {
      "command": "python",
      "args": ["-m", "quantgpt"]
    }
  }
}

Then let the Agent work: "在沪深300上挖掘高 fitness 的因子，目标 WQ BRAIN 可提交"

Option 2: Expression Mode (No LLM Required)

# Direct expression backtest via API
curl -X POST http://localhost:8003/api/v1/auto_backtest \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <token>" \
  -d '{"expression": "rank(close / ts_mean(close, 20))", "universe": "hs300"}'

Windows Quick Start

Windows 用户不需要 make 和 restart.sh，手动执行即可：

# 1. 克隆项目
git clone https://github.com/Miasyster/QuantGPT.git
cd QuantGPT

# 2. 创建虚拟环境并安装依赖
python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt

# 3. 构建前端（需要 Node.js，从 nodejs.org 下载 LTS 版本）
cd frontend && npm install && npm run build && cd ..

# 4. 启动服务
python -m quantgpt --transport http
# 浏览器打开 http://localhost:8003

注意：

• 推荐 Python 3.11 或 3.12（3.14 太新，部分依赖可能不兼容）
• 如果端口被占用：netstat -ano | findstr :8003 查进程，taskkill /PID <pid> /F 杀掉
• 也可以使用 WSL2（wsl --install），体验与 macOS/Linux 完全一致

Zero config by default: SQLite database, baostock + akshare free data. See full Quick Start guide for details.

# Edit .env, add your DeepSeek API key (~$0.001 per query)
DEEPSEEK_API_KEY=sk-your-key-here

pip install "quantgpt[postgresql]"
# Edit .env:
DATABASE_URL=postgresql+asyncpg://quantgpt:password@localhost:5432/quantgpt
alembic upgrade head

# Debt-momentum composite — BRAIN submitted, Fitness 1.26, Sharpe 1.77
-1 * rank(ts_av_diff(close, 10)) + rank(debt / enterprise_value)

# VWAP decay reversal — BRAIN submitted, Fitness 1.07, Sharpe 1.69
-1 * rank(ts_decay_linear(close / vwap, 10))

# Returns-volume momentum — BRAIN submitted, Fitness 1.03, Sharpe 1.60
-1 * rank(ts_decay_linear(returns * volume / adv20, 5))

# 20-day momentum
rank(close / ts_mean(close, 20))

# Low volatility
rank(-1 * ts_std(close/ts_shift(close,1)-1, 20))

# Decay-weighted correlation
decay_linear(rank(ts_corr(vwap, volume, 10)), 5)

Project Structure

quantgpt/
├── quantgpt/                    # Backend (Python)
│   ├── expression_parser.py     # Factor expression parser (50+ ops, WQ compatible)
│   ├── backtest.py              # Rank-based group backtest engine
│   ├── market_data.py           # baostock/akshare → Parquet cache
│   ├── api_server.py            # FastAPI REST API + SSE
│   ├── mcp_server.py            # FastMCP server (14 tools — Agent's toolkit)
│   ├── iteration.py             # 3-phase evolutionary iteration
│   ├── mutation_engine.py       # 8 directed mutation strategies
│   ├── crossover_engine.py      # High-score factor crossover
│   ├── meta_evolution.py        # Adaptive strategy selector
│   ├── trajectory_analyzer.py   # Trajectory quality metrics
│   ├── anti_overfit.py          # 4 statistical anti-overfit tests
│   ├── rolling_validator.py     # Walk-forward validation
│   ├── wq_simulate.py           # WQ BRAIN dollar-neutral simulator
│   ├── wq_brain_client.py       # WQ BRAIN API integration
│   ├── neutralize.py            # Industry & cap neutralization
│   ├── daily_summary.py         # LLM-powered daily market report
│   └── routes/                  # API route modules
├── frontend/                    # React 18 + TypeScript + Tailwind CSS 4
│   └── src/components/          # Monitoring dashboard
├── scripts/
│   └── factor_miner.py          # Batch factor evaluation toolkit
├── tests/                       # 74 tests (parser + backtest + WQ simulate)
├── example_factor/              # BRAIN validation screenshots
└── docs/                        # Architecture, API, MCP, Mining guides

Limitations

• Daily frequency only — no intraday backtesting
• A-share market only — China mainland equities
• Agent quality depends on LLM — better models produce better factors

License

MIT — Copyright (c) 2026 Miasyster

This repository is the original source of the QuantGPT factor research engine. Derivative works should retain the copyright notice and comply with the MIT License terms. See NOTICE for details.

_{Past factor performance does not guarantee future returns. This project does not constitute investment advice.}