Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From factor-researcher
Combines factor libraries into composite signals and quintile-backtests them under transaction costs, producing long-short returns, monotonicity, turnover, and tearsheets for portfolio-level evaluation.
npx claudepluginhub minihellboy/factorminer --plugin factor-researcherHow this skill is triggered — by the user, by Claude, or both
Slash command
/factor-researcher:factor-backtestThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A library of individually-decent factors is not a strategy. This skill combines them into one composite signal and backtests the portfolio that signal implies — the level at which transaction costs and capacity actually bite.
Recomputes factor library metrics (IC, ICIR, win rate, turnover) on held-out data and surfaces train→test decay to judge out-of-sample quality.
Builds robust production-grade backtesting systems for trading strategies, avoiding biases with point-in-time data, walk-forward analysis, and realistic cost models for reliable performance estimates.
Backtests crypto/stock trading strategies on historical data. Computes Sharpe/Sortino ratios, drawdowns; plots equity curves; optimizes parameters via grid search.
Share bugs, ideas, or general feedback.
A library of individually-decent factors is not a strategy. This skill combines them into one composite signal and backtests the portfolio that signal implies — the level at which transaction costs and capacity actually bite.
factorminer combine output/run1/factor_library.json \
--data path/to/market_data.csv \
--method all --fit-period train --eval-period test
--method — equal-weight, ic-weighted, orthogonal, or all to compare every method.--fit-period — split used to fit weights / run selection (use train).--eval-period — split used to score the composite (use test).--selection — optional pre-filter: lasso, stepwise, xgboost, or none.--top-k — keep only the top-K factors before combining.The report gives composite IC Mean, ICIR, Long-Short return, Monotonicity, and Avg Turnover.
For the visual portfolio view — quintile returns, IC time series, correlation heatmap:
factorminer -o output/run1 visualize output/run1/factor_library.json \
--data market_data.csv --period test --tearsheet --quintile --correlation
Avg Turnover means the gross return is optimistic; FactorMiner's transaction-cost model is what makes the net number honest.orthogonal and equal-weight disagree sharply, the library has redundant or unstable factors; revisit factor-evaluation.train, score on test — never fit and score on the same split.