闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > quant-research-platform
q

量化研究平台

技能标识：quant-research-platform

Advanced quantitative research platform for multi-factor analysis, factor mining, backtesting, and portfolio optimization. Includes 100+ alpha factors, IC/IR analysis, factor correlation, and intelligent factor combination.

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 1.0.0
检测标记
后台标记通过
免费
免费获取
1
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

量化研究平台

量化研究平台

面向专业量化开发者和研究者的高级量化研究平台。

功能特性

1. 多因子研究

  • - 100+ Alpha因子：技术面、基本面、情绪面、另类数据
  • 因子挖掘：自动化因子发现与评估
  • 因子分析：IC、IR、IC衰减、换手率分析
  • 因子组合：智能因子加权与组合

2. 回测引擎

  • - 历史回测：完整历史模拟
  • 滚动优化：样本外验证
  • 蒙特卡洛：概率化绩效估计
  • 交易成本：真实成本建模

3. 投资组合优化

  • - 均值-方差：经典马科维茨优化
  • 风险平价：等风险贡献
  • Black-Litterman：贝叶斯先验融合
  • ACL：学术因子模型优化
  • 凯利准则：最优杠杆计算

4. 风险管理

  • - VaR/CVaR：风险价值分析
  • 压力测试：情景分析
  • 因子暴露：风格暴露监控
  • 回撤控制：动态仓位调整

5. 策略开发

  • - 动量策略：趋势跟踪、突破策略
  • 均值回归：统计套利
  • 统计模型：配对交易、协整
  • 机器学习策略：XGBoost、LightGBM、LSTM

安装

bash
pip install pandas numpy scikit-learn xgboost lightgbm scipy statsmodels
pip install akshare tushare

使用说明

因子研究

python from quant_research import FactorResearch

research = FactorResearch()

添加因子

research.addfactor(momentum20d, computemomentum20d) research.addfactor(volatility60d, computevolatility60d) research.addfactor(roe, computeroe)

分析因子表现

icanalysis = research.analyzeic( factors=[momentum20d, volatility60d], lookback=252 )

print(fIC: {icanalysis[icmean]:.3f})
print(fIR: {ic_analysis[ir]:.3f})

回测

python from quant_research import BacktestEngine

bt = BacktestEngine(
start_date=2020-01-01,
end_date=2024-12-31,
initial_capital=1000000
)

添加策略

bt.addstrategy(MomentumStrategy(n=20, holdingperiod=60))

运行回测

results = bt.run()

print(f年化收益率: {results[annual_return]:.2%})
print(f夏普比率: {results[sharpe_ratio]:.2f})
print(f最大回撤: {results[max_drawdown]:.2%})

投资组合优化

python from quant_research import PortfolioOptimizer

opt = PortfolioOptimizer(returns_df)

均值-方差优化

weights = opt.meanvariance(targetreturn=0.15)

风险平价

weights = opt.risk_parity()

Black-Litterman

weights = opt.blacklitterman(marketcap_weights, views)

因子库

技术因子
因子描述
returns5d/20d/60d累计收益率
volatility20d/60d
滚动波动率 |

| momentum_20d/60d | 价格动量 | | volume_ratio | 相对成交量 | | turnover_rate | 换手率 | | rsi_14d | RSI指标 |

基本面因子
因子描述
pe_ttm市盈率
pb
市净率 |

| roe | 净资产收益率 | | roa | 总资产收益率 | | debt_ratio | 资产负债率 | | gross_margin | 毛利率 |

情绪因子
因子描述
newssentiment新闻情绪评分
socialbuzz
社交媒体提及量 |

| analyst_rating | 分析师共识评级 |

API参考

FactorResearch
方法描述
addfactor(name, func)添加自定义因子
analyzeic(factors)
IC/IR分析 |

| factor_correlation() | 相关性矩阵 | | optimal_weights() | 因子组合 |

BacktestEngine
方法描述
add_strategy(strategy)添加交易策略
run()
执行回测 |

| get_metrics() | 绩效指标 | | get_trades() | 交易记录 |

PortfolioOptimizer
方法描述
meanvariance()马科维茨优化
riskparity()
风险平价权重 |

| black_litterman() | 贝叶斯优化 | | kelly() | 凯利准则 |

绩效指标

  • - 年化收益率
  • 夏普比率
  • 索提诺比率
  • 卡玛比率
  • 最大回撤
  • 胜率
  • 盈亏比
  • 交易次数

应用场景

  • - 因子发现：寻找新的Alpha因子
  • 策略开发：构建和测试策略
  • 组合构建：优化资产配置
  • 风险管理：监控和控制风险
  • 研究自动化：系统化研究工作流

高级功能

机器学习集成

python from quant_research.ml import FactorModel

model = FactorModel(algorithm=xgboost)
model.train(factors, returns)
model.predict()

特征重要性

importance = model.feature_importance()

另类数据

python from quant_research import AlternativeData

alt = AlternativeData()

卫星图像

sat = alt.satellitedata(companyname)

网络流量

traffic = alt.web_traffic(url)

供应链

supply = alt.supplychain(companyname)

相关链接

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 quant-research-platform-1776100983 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 quant-research-platform-1776100983 技能

通过命令行安装

skillhub install quant-research-platform-1776100983

下载

⬇ 下载 quant-research-platform v1.0.0（免费）

文件大小: 7.38 KB | 发布时间: 2026-4-14 11:07

v1.0.0 最新 2026-4-14 11:07
Initial release of quant-research-platform.

- Multi-factor research with 100+ alpha factors and automated factor mining/evaluation
- Comprehensive backtesting engine with historical, walk-forward, and Monte Carlo analysis, including transaction costs
- Advanced portfolio optimization: mean-variance, risk parity, Black-Litterman, ACL, and Kelly criterion
- Integrated risk management: VaR/CVaR, stress testing, factor exposure, drawdown control
- Supports strategy development with classic and machine learning (XGBoost, LightGBM, LSTM) approaches
- Extensive API for factor research, backtesting, and optimization
- Built-in support for technical, fundamental, sentiment, and alternative data factors

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部