ml4t-lookahead-bias
Detect future information leaking into features, labels, or evaluation. Use when any pipeline step might expose data not yet available at prediction time.
38,472 Skills
搜索范围为本次公开目录;榜单和数量均为记录时的数据。
Detect future information leaking into features, labels, or evaluation. Use when any pipeline step might expose data not yet available at prediction time.
Secondary model predicts whether a primary signal will be profitable. Use when sizing positions or filtering low-conviction trades from a base alpha model.
Handle changing statistical properties in financial time series. Use when features or model performance degrade over time.
Ensure data reflects what was known at each decision point, not revised or restated values. Use when joining fundamental, macro, or alternative data to price series.
Polars-first data processing patterns for financial data. Use when writing efficient grouped, windowed, or lazy-evaluated data transformations.
Convert signals to position sizes using volatility targeting and risk budgets. Use when scaling trade size relative to conviction and portfolio risk.
Market regimes as conditioning features for risk scaling, not timing signals. Use when incorporating regime detection into strategy logic.
Compute portfolio risk measures including drawdown, VaR, CVaR, and tail metrics. Use when assessing portfolio risk beyond simple return statistics.
Test strategy robustness to parameter variation and detect overfitting cliffs. Use when validating that performance is stable across parameter perturbations.
Account for delisted and removed securities in historical analysis. Use when constructing universes or computing cross-sectional features to avoid survivor-only inflation.
Generate comprehensive performance reports from backtest returns. Use when summarizing backtest results for review or comparison.
Estimate whether a strategy can survive spread, slippage, and market impact before full simulation. Use when screening strategy feasibility early.
Label trades using profit-target, stop-loss, and time barriers with volatility-adaptive thresholds. Use when creating supervised labels for financial time series.
Systematic data quality validation before modeling. Use when checking for gaps, outliers, stale prices, or schema violations in datasets.
Remove git worktrees safely without force. Use when the user asks to remove, clean up, or delete git worktrees.
目录记录日期:2026-11-21