Documentation

Pairs Trading

Statistical arbitrage with pair discovery, signals, and spread analysis

Open in App

Enterprise Feature

This feature is available on the Enterprise plan. The documentation below describes its full capabilities so you can evaluate whether it fits your workflow. Contact us to learn more about upgrading your access.

Overview

Pairs Trading is a statistical arbitrage tool that identifies pairs of stocks with historically correlated price movements. When the spread between paired stocks deviates from its historical norm, it generates signals to trade the convergence back to the mean. This is a market-neutral strategy that can profit regardless of overall market direction.

Tabs

Discovery

Automated pair discovery using cointegration tests, correlation analysis, and sector grouping. Finds the best candidate pairs from the stock universe.

  • -Cointegration test results (p-values)
  • -Correlation coefficients
  • -Half-life of mean reversion
  • -Sector and industry pair grouping
Signals

Active trading signals for discovered pairs. Shows when spreads have deviated significantly from their historical mean.

  • -Z-score of current spread (deviation from mean)
  • -Signal direction (long/short the spread)
  • -Entry and exit thresholds
  • -Signal strength and confidence
Spread

Detailed spread analysis for a selected pair including historical spread chart, Z-score visualization, and statistical properties.

  • -Historical spread time series chart
  • -Z-score overlay with entry/exit bands
  • -Rolling correlation and cointegration stability
  • -Spread distribution histogram
History

Backtested trade history for pair strategies showing completed round-trip trades, P&L, and aggregate performance statistics.

  • -Round-trip trade log with entry/exit dates and prices
  • -Per-trade and cumulative P&L
  • -Win rate, average hold time, profit factor
  • -Equity curve and drawdown analysis

Key Concepts

ConceptDescription
CointegrationStatistical property where two price series maintain a stable long-run relationship even if they wander individually
SpreadThe price difference (or ratio) between the two paired stocks
Z-ScoreNumber of standard deviations the spread is from its historical mean
Half-LifeExpected time for the spread to revert halfway back to the mean (shorter is better)
Mean ReversionThe tendency of the spread to return to its historical average after deviating

How to Use

  • Start with the Discovery tab to review pre-screened pair candidates
  • Focus on pairs with low cointegration p-values (below 0.05) for statistical reliability
  • Check the Signals tab for pairs currently showing trading signals
  • Use the Spread tab to visualize the current spread condition for a specific pair
  • Review History for backtested performance of the pairs strategy

Warning

Pairs trading requires careful risk management. Cointegration relationships can break down (structural breaks), and spreads can widen further before reverting. Always use appropriate position sizing and stop-loss levels.

Combining with Other Tools

  • Use Factor Intelligence to find stocks with similar factor profiles as pair candidates
  • Cross-reference pair signals with Market Regimes — mean reversion strategies work best in sideways/low-vol regimes
  • Check Fundamental Ranking for both stocks in a pair to understand if the spread deviation is fundamentally justified
  • Use the Chart page to visually inspect the spread and confirm the statistical signals

This platform provides data and analysis tools for educational and informational purposes only. Nothing on this platform constitutes financial advice, investment recommendations, or solicitation to buy or sell any securities. Always conduct your own research and consult with a qualified financial advisor before making investment decisions.