Back to Details

longbridge-correlation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

longbridge-correlation

longbridge-correlation

Computes pairwise return correlations and cointegration statistics for a basket of 2–10 symbols. Helps identify diversification opportunities, highly correlated pairs (pairs-trading candidates), and portfolio concentration risks.
Response language: match the user's input language — Simplified Chinese / Traditional Chinese / English.
计算一篮子2-10个标的的两两收益相关性与协整统计数据。帮助识别多元化机会、高度相关的标的对（配对交易候选）以及投资组合集中度风险。
响应语言：匹配用户输入语言——简体中文/繁体中文/英文。

When to use

使用场景

  • User supplies 2–10 symbols and asks for correlation analysis, whether two stocks move together, rolling correlation trends, or pairs-trading pre-screening.
  • Triggers: "AAPL MSFT GOOGL 相关矩阵", "TSLA 和 NVDA 滚动相关", "correlation matrix for my watchlist", "协整检验 700.HK 5.HK".
  • 用户提供2-10个标的，并要求进行相关性分析、判断两只股票是否同涨同跌、滚动相关性趋势或配对交易预筛选。
  • 触发示例："AAPL MSFT GOOGL 相关矩阵"、"TSLA 和 NVDA 滚动相关"、"correlation matrix for my watchlist"、"协整检验 700.HK 5.HK"。

Workflow

工作流程

  1. For each symbol, fetch 252 daily candles: 
    longbridge kline <SYMBOL> --period day --count 252 --format json
  2. Align all series on 
    time
    ; drop dates missing in any series.
  3. Compute daily log-returns for each symbol.
  4. Pearson correlation matrix: pairwise Pearson correlation of returns; flag pairs with |ρ| > 0.8 (high) or < 0.2 (low).
  5. Spearman correlation (rank-based, robust to outliers): compute alongside Pearson for comparison.
  6. Rolling 60-day correlation for the highest-correlated pair: show trend over time.
  7. Cointegration screen (for pairs only):
    • OLS spread residuals → ADF test → report p-value and verdict
    • Half-life = −ln(2) / OLS slope of Δspread ~ spread_{t-1}
  8. Output correlation matrix heatmap description (text-based) and a summary of key relationships.
Run 
longbridge kline --help
to confirm current flag names.
  1. 为每个标的获取252条日K线数据： 
    longbridge kline <SYMBOL> --period day --count 252 --format json
  2. 按
    time
    对齐所有序列；删除任何序列中缺失的日期。
  3. 计算每个标的的日对数收益率。
  4. Pearson相关矩阵：计算收益的两两Pearson相关性；标记|ρ| > 0.8（高度相关）或 < 0.2（低度相关）的标的对。
  5. Spearman相关性（基于排名，对异常值鲁棒）：与Pearson相关性一同计算以作对比。
  6. 最高相关标的对的60日滚动相关性：展示随时间变化的趋势。
  7. 协整筛选（仅针对标的对）：
    • OLS价差残差 → ADF检验 → 报告p值和结论
    • 半衰期 = −ln(2) / Δspread ~ spread_{t-1}的OLS斜率
  8. 输出基于文本的相关矩阵热图描述以及关键关系总结。
运行
longbridge kline --help
确认当前参数名称。

CLI

命令行界面（CLI）

bash
longbridge kline --help
bash
longbridge kline --help

Repeat for each symbol (2–10)

为每个标的重复执行（2-10个）

longbridge kline <SYMBOL> --period day --count 252 --format json
undefined
longbridge kline <SYMBOL> --period day --count 252 --format json
undefined

Output

输出

Metric简体繁體English
Pearson ρ matrix皮尔森相关矩阵皮爾森相關矩陣Pearson correlation matrix
Spearman ρ斯皮尔曼相关斯皮爾曼相關Spearman correlation
Rolling 60d corr60日滚动相关60日滾動相關60-day rolling correlation
ADF p-value协整 p 值協整 p 值ADF p-value
Half-life半衰期（天）半衰期（天）Half-life (days)
Cluster相关聚类相關聚類Correlation cluster
Present: (1) full correlation matrix table with colour coding (high ≥ 0.8 = red, low ≤ 0.2 = green); (2) rolling-correlation narrative; (3) cointegration results if relevant; (4) portfolio implication note. Cite Longbridge Securities / 数据来源：长桥证券 / 數據來源：長橋證券.
指标简体繁体English
Pearson ρ matrix皮尔森相关矩阵皮爾森相關矩陣Pearson correlation matrix
Spearman ρ斯皮尔曼相关斯皮爾曼相關Spearman correlation
Rolling 60d corr60日滚动相关60日滾動相關60-day rolling correlation
ADF p-value协整 p 值協整 p 值ADF p-value
Half-life半衰期（天）半衰期（天）Half-life (days)
Cluster相关聚类相關聚類Correlation cluster
展示内容：(1) 带颜色编码的完整相关矩阵表格（高度相关≥0.8 = 红色，低度相关≤0.2 = 绿色）；(2) 滚动相关性说明；(3) 相关的协整结果；(4) 投资组合影响提示。标注Longbridge Securities / 数据来源：长桥证券 / 數據來源：長橋證券。

Error handling

错误处理

Situation简体回复繁體回復English reply
command not found: longbridge
回退到 MCP 或提示安装 longbridge-terminal回退到 MCP 或提示安裝 longbridge-terminalFall back to MCP or install longbridge-terminal
not logged in
/ 
unauthorized
请运行 
longbridge auth login
請執行 
longbridge auth login
Run 
longbridge auth login
Only 1 symbol provided至少需要2个标的才能计算相关性至少需要2個標的Need at least 2 symbols
> 10 symbols最多支持10个标的，请精简列表最多支持10個標的Max 10 symbols; please reduce list
Other stderr直接显示原始错误直接顯示原始錯誤Surface verbatim
场景简体回复繁体回复English reply
command not found: longbridge
回退到 MCP 或提示安装 longbridge-terminal回退到 MCP 或提示安裝 longbridge-terminalFall back to MCP or install longbridge-terminal
not logged in
/ 
unauthorized
请运行 
longbridge auth login
請執行 
longbridge auth login
Run 
longbridge auth login
仅提供1个标的至少需要2个标的才能计算相关性至少需要2個標的Need at least 2 symbols
> 10个标的最多支持10个标的，请精简列表最多支持10個標的Max 10 symbols; please reduce list
其他标准错误输出直接显示原始错误直接顯示原始錯誤Surface verbatim

MCP fallback

MCP回退方案

Use 
mcp__longbridge__candlesticks
with 
period=Day
, 
count=252
per symbol when CLI is unavailable.
当CLI不可用时，对每个标的使用
mcp__longbridge__candlesticks
，参数为
period=Day
、
count=252
。

Related skills

相关技能

  • longbridge-kline
    — raw OHLCV data
  • longbridge-pairs-trading
    — execute a pairs trade after correlation pre-screen
  • longbridge-multifactor
    — factor correlation and collinearity check
  • longbridge-performance-attribution
    — covariance matrix for factor decomposition
  • longbridge-kline
    — 原始OHLCV数据
  • longbridge-pairs-trading
    — 相关性预筛选后执行配对交易
  • longbridge-multifactor
    — 因子相关性与共线性检验
  • longbridge-performance-attribution
    — 用于因子分解的协方差矩阵

File layout

文件结构

longbridge-correlation/
└── SKILL.md
longbridge-correlation/
└── SKILL.md