Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From factor-researcher
Recomputes factor library metrics (IC, ICIR, win rate, turnover) on held-out data and surfaces train→test decay to judge out-of-sample quality.
npx claudepluginhub minihellboy/factorminer --plugin factor-researcherHow this skill is triggered — by the user, by Claude, or both
Slash command
/factor-researcher:factor-evaluationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Mining proposes factors; evaluation decides whether to believe them. This skill recomputes a library's metrics on a chosen split and exposes overfitting.
Runs FactorMiner benchmark workflows: Table 1 Top-K freeze benchmark, memory/strategy ablations, transaction-cost pressure tests, and the full suite. Use to compare against baselines or reproduce paper results.
Builds financial models, backtests trading strategies, analyzes market data with risk metrics, portfolio optimization, and statistical arbitrage.
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.
Mining proposes factors; evaluation decides whether to believe them. This skill recomputes a library's metrics on a chosen split and exposes overfitting.
See references/metrics.md for precise metric definitions (IC vs. paper-IC, ICIR, redundancy correlation).
factorminer evaluate output/run1/factor_library.json \
--data path/to/market_data.csv \
--period test
--period selects the split: train, test, or both. Always lead with test — in-sample IC is not evidence.
The output table reports, per factor: IC Mean, Paper IC, Abs IC, Paper ICIR, Win%, and Turnover. The summary block gives library-level means and the IC range.
factorminer evaluate output/run1/factor_library.json --data market_data.csv --period both
--period both adds a decay table (train Paper IC → test Paper IC → delta). A large negative delta is the signature of an overfit factor. Report decay honestly; do not quote the train number as the headline.
To shortlist the strongest signals only:
factorminer evaluate output/run1/factor_library.json --data market_data.csv --period test --top-k 10
The top-K-by-IC table is the signal shortlist — the natural handoff to a research-idea workflow that wants to know which quantitative signals are currently working. The MCP screen_factors tool returns this same shortlist directly.
factor-backtest.train metrics as the result. The deliverable is the test number.