claude

factor-researcher

Systematic quantitative alpha-factor research: validate market data, mine a factor library, evaluate IC/ICIR, backtest a composite, benchmark, and report — powered by the FactorMiner engine

130 on GitHubby FactorMiner Teamv0.1.0MITupdated 26 days ago
/

Plugin factor-researcher from marketplace factorminer in minihellboy/factorminer. Commands read from the repo's manifest — 26 days ago.

This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (7)

  • factor-backtest

    Combine a factor library into a composite signal and quintile-backtest it under transaction costs — long-short return, monotonicity, turnover, and tearsheets. Use for the portfolio-level view that single-factor IC does not give. Triggers on "backtest", "composite signal", "combine factors", "long-sh

  • factor-benchmark

    Run FactorMiner benchmark workflows — the Table 1 Top-K freeze benchmark, memory and strategy ablations, transaction-cost pressure tests, and the full suite. Use to compare FactorMiner against baselines or to reproduce paper results. Triggers on "benchmark", "ablation", "compare to baseline", "repro

  • factor-data

    Validate, resample, and ingest market data for factor mining. Schema-checks OHLCV files (CSV/Parquet/HDF5), resamples bar frequencies, and pulls live data from external MCP connectors (FactSet, Daloopa, Morningstar). Use before any mining run. Triggers on "validate data", "check my dataset", "resamp

  • factor-evaluation

    Evaluate a factor library — recompute Information Coefficient (IC), ICIR, win rate, and turnover on held-out data, and surface train→test decay. Use to judge how good a mined library actually is out of sample. Triggers on "evaluate factors", "compute IC", "how good is this library", "factor metrics"

  • factor-mining

    Discover alpha factors by running the FactorMiner research engine — the paper-faithful Ralph loop or the enhanced Helix loop (causal validation, regime conditioning, multi-specialist debate, canonicalization). Use to generate a new factor library from a validated dataset. Triggers on "mine factors",

  • factor-report

    Generate static reports, tearsheets, and exports from FactorMiner artifacts — markdown/HTML research notes, plots, and library exports (JSON/CSV/formulas). Use to package a finished research run for review. Triggers on "generate report", "factor report", "research note", "tearsheet", "visualize fact

  • research-ingestion

    Absorb external research reports/papers into structured, retrievable hypothesis cues via FactorMiner's Report-to-Memory Absorption (RMA) service — an OHLCV-eligibility gate, a mechanism-family classifier, and research-path cues that feed factor generation prompts. Use to turn a report fragment into

Slash commands (7)

  • /factor-researcher:backtest

    Combine factors into a composite signal and quintile-backtest it

  • /factor-researcher:benchmark

    Run a FactorMiner benchmark — Table 1, ablation, cost pressure, or suite

  • /factor-researcher:evaluate

    Evaluate a factor library's out-of-sample IC, ICIR, and decay

  • /factor-researcher:mine

    Mine a new alpha-factor library from a market dataset

  • /factor-researcher:report

    Generate a research note, plots, and exports from a finished run

  • /factor-researcher:screen

    Rank a factor library and return the strongest signals

  • /factor-researcher:validate-data

    Validate or fetch a market dataset before mining

Subagents (1)

  • factor-researcher

    Runs systematic quantitative alpha-factor research end to end — validates a market dataset, mines a factor library with the FactorMiner engine, evaluates it (IC/ICIR/correlation), backtests a composite signal under transaction costs, benchmarks it against baselines, and packages a research note. Use

MCP servers (12)

  • factorminer

    runs: factorminer mcp-serve

  • factset

    connects to: https://mcp.factset.com/mcp

  • daloopa

    connects to: https://mcp.daloopa.com/server/mcp

  • morningstar

    connects to: https://mcp.morningstar.com/mcp

  • sp-global

    connects to: https://kfinance.kensho.com/integrations/mcp

  • moodys

    connects to: https://api.moodys.com/genai-ready-data/m1/mcp

  • mtnewswire

    connects to: https://vast-mcp.blueskyapi.com/mtnewswires

  • aiera

    connects to: https://mcp-pub.aiera.com

  • lseg

    connects to: https://api.analytics.lseg.com/lfa/mcp

  • pitchbook

    connects to: https://premium.mcp.pitchbook.com/mcp

  • chronograph

    connects to: https://ai.chronograph.pe/mcp

  • egnyte

    connects to: https://mcp-server.egnyte.com/mcp

View source on GitHub

Maintain factor-researcher?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted