AI 原生 A 股投研中枢|百万级本地数据 × 量化实验 × 多模型研究 × 可追溯决策。Research deeper. Decide with evidence. · Local-first · Hermes / MCP.
-
Updated
Oct 27, 2026 - Python
AI 原生 A 股投研中枢|百万级本地数据 × 量化实验 × 多模型研究 × 可追溯决策。Research deeper. Decide with evidence. · Local-first · Hermes / MCP.
LawVM compiles human-written amendment acts into auditable point-in-time legal text-state. It treats legislation as executable state transitions, preserving provenance, replay evidence, and divergence findings across jurisdictions.
Evidence-traceable, point-in-time multi-agent research for China A shares
面向 AI 的高性能 A 股因子回测引擎:固定完整基准较 Qlib 快 14.34×,内置 PIT 股票池、净额换仓、涨跌停/停牌、双边成本与滚动检验。
Write the signal once; it is already production code.
Stop silent data leakage in ML training pipelines.
Open-source point-in-time membership tables for NSE (India): 42 equity indices, F&O segment, quarterly shareholding, and cash-market EOD OHLC — derived from public NSE press releases and circulars.
Free CC0 point-in-time US fundamentals proof pack — 5 companies, 225 annual rows across their latest 3 fiscal years, full methodology, no signup.
Reusable Agent Skills for quantitative finance research, extracted from the Aria toolchain.
Content-addressed, replay-verifiable snapshots of free US-listed equity data sources.
An honesty harness for LLM trading research: point-in-time discipline, leakage self-tests, and forward-only LLM feature collection. A-shares + US equities.
Leakage-safe point-in-time features and idempotent DuckDB ingestion
Yet Another Stock Screener — screen stocks using fundamental signals, backtest with point-in-time data, evaluate with Monte Carlo analysis
Historical RV15 forecasts for six U.S. stocks. Option state improves both families; the mixed B2 block improves the linear model only. Source-time assumptions, placebo and final-window limits remain material. Public aggregate checks are not an independent licensed-data replication.
Point-in-time S&P 500 pipeline: SEC 8-K tone (Loughran-McDonald) and Google Trends signals, by-date IC with stated statistical power; runs daily on GitHub Actions.
An honest, survivorship-bias-corrected backtesting engine. Market-agnostic — Indian equities (Nifty 50/100/200/500) wired in out of the box, extensible to US/global via yfinance. Tax-aware, free data, Python + DuckDB.
Point-in-time SEC filing retrieval: hybrid search, citation-verified answers with abstention, typed financial facts, filing diffs, and reproducible signal studies. Live at thefdre.com.
미국주식 팩터 엔진 + ETF 전술배분 검증 — point-in-time·생존편향 보정 데이터 위에서 워크포워드를 Deflated Sharpe·PBO 로 게이팅. 채택만이 아니라 기각도 함께 공개 · US equity factor engine with walk-forward validation
Point-in-time, reproducible A-share factor research and execution backtesting platform.
한국 주식 데이터 수집 Airflow 파이프라인 — 시세·수급·실적·컨센서스를 TimescaleDB 에 적재하고 상장폐지 종목까지 백필해 생존편향을 저장 층에서 차단 · Airflow pipeline for Korean market data, delisted names included
To associate your repository with the point-in-time topic, visit your repo's landing page and select "manage topics."