The Library

Concept family

Performance, Backtesting & Validation

Return, risk and trade metrics plus the anti-overfitting methodology — the honesty layer.

Validation is where a trading idea meets evidence. This family collects the metrics used to summarize performance, such as win rate and the Sharpe ratio, alongside the methodology that keeps those numbers honest: testing on data the strategy has never seen and checking that results survive small changes in settings.

The recurring theme is that an impressive backtest is easy to produce and easy to misread. A high win rate can coexist with poor risk-reward, a strong Sharpe ratio can mask tail risk, and any metric can be inflated by fitting parameters to history. The entries here explain what each number does and does not tell you, and how to structure tests so a good result is more likely to reflect a real effect than a curve fit.

Start here

Return/risk metrics

Measures that weigh returns against the risk taken to earn them, with the Sharpe ratio as the standard reference point.

Sharpe Ratio1CAGRCalmar RatioDrawdown StatisticsExtended Risk-adjusted RatiosInformation RatioMartin RatioSignificance of ReturnsSortino RatioSQN

Trade metrics

Statistics built from individual trade outcomes, where a number like win rate only becomes meaningful next to average win and loss size.

Win Rate3Cost SensitivityExpectancyMAE/MFE DistributionsProfit FactorThroughput Stats

Validation methodology

Procedures that help separate genuine edges from curve fits, including holding out unseen data and checking stability across nearby parameter values.

In-sample / Out-of-sample Split1Parameter Stability1Benchmark Comparison DisciplineBias TaxonomyCost-model RealismDeflated Sharpe RatioForward/paper-trading ConfirmationLive Decay TrackingMultiple-testing CorrectionProbability of Backtest OverfittingPurged Cross-validationRandomization TestsRobustness TestingWalk-forward Analysis