Finance Data Research Hub
AI 驅動的美股投資研究平台 — 基本面分析、技術分析、市場數據、SEC 文件，全部繁體中文。
Live site: yennanliu.github.io/finance_data (English + 繁體中文)
An automated research pipeline for US (and Taiwan) equities. Scheduled jobs fetch
market and SEC data, an LLM writes structured reports in Traditional Chinese, a
nightly audit checks every figure it can, and the results are published as a
static MkDocs site.
Features
| |
|---|
| AI reports | 12 analysis types. Fundamental and technical reports run daily; earnings-call, insider, 13F, valuation and more run on demand |
| Checked figures | Derived numbers (TTM, FCF, WACC, multiples) are computed in Python and quoted by the model. The §8.8 fair-value sum is recomputed and corrected after generation |
| Market Data | 10-year daily OHLCV plus SEC quarterly fundamentals per ticker: candles, drawdown, volatility, financial statements, valuation bands, DCF and reverse DCF. Downloadable as CSV / JSON |
| Market news | Daily per-ticker digest from Yahoo, RSS feeds and Perplexity Discover |
| QA audit | Nightly rule-based checks plus a cross-provider LLM review, committed to qa/ |
| SEC filings | 10-K, 10-Q, 13-F and 6-K archives (10-k/, 10-q/, 13-f/, 6-k/) |
| Research notes | NotebookLM deep dives (notebook_llm/) and investor-day materials (investor_day/) |
Coverage
- Daily fundamental (36): 0050, 2330.TW, TSLA, PL, GRAB, TSM, GOOG, AMZN,
MSFT, SOFI, PLTR, RKLB, ONDS, AVAV, KTOS, META, AMD, NVDA, NU, VST, ORCL, INTC,
SPCX, AVGO, NBIS, MU, SKHY, WDC, SNDK, MRVL, SOXQ, SOXX, WQTM, VTI, QQQ, ROBO
- Daily technical (25): the first 25 of the above (0050 … NBIS)
- Analysis types (12):
fundamental-analysis, technical-analysis,
stock-eval, stock-valuation, financial-report-analyst,
earnings-call-analysis, insider-trading, institutional-ownership,
sector-analysis, economics-analysis, portfolio-review, report-generator
The schedule is data-driven: scripts/.ticker_schedule.json.
How it works
┌──────────────┐ ┌──────────────────┐ ┌──────────────┐ ┌──────────────┐
│ Data fetch │───▶│ LLM analysis │───▶│ QA audit │───▶│ Publish │
│ yfinance │ │ Gemini → OpenAI │ │ rules + LLM │ │ MkDocs │
│ SEC XBRL │ │ (Claude opt-in) │ │ judge │ │ GitHub Pages │
│ scrapers │ │ 繁中 reports │ │ nightly │ │ nightly │
└──────────────┘ └──────────────────┘ └──────────────┘ └──────────────┘
- Fetch.
yfinance, Finviz / StockAnalysis / Roic.ai scrapers and SEC
companyfacts. Prices and fundamentals are kept as committed CSV stores in
data/.
- Analyse.
scripts/generate_analysis.py builds a context per analysis type
and calls the LLM chain (fundamental reports: OpenAI gpt-6-luna first, Gemini as fallback; other types: Gemini gemini-3.8-flash first, OpenAI as fallback).
Reports land in ai_gen_report/.
- Audit.
qa_report_quality.yml checks reports nightly. See
docs/QA_AUDIT.md.
- Publish.
scripts/build_docs.py turns reports and stores into the site;
deploy.yml builds and deploys it at 04:00 UTC.
Quick start
Requires uv. It installs the pinned Python (3.11)
for you.
Clone (lightweight)
The full history is ~1 GB, mostly PDFs. A partial clone with sparse checkout
skips the PDF folders:
git clone --filter=blob:none --no-checkout [email protected]:yennanliu/finance_data.git
cd finance_data
git sparse-checkout set --no-cone '/*' '!notebook_llm/' '!10-k/' '!10-q/'
git checkout main
Set the sparse patterns before the first checkout. git sparse-checkout disable
brings the PDFs back.
Generate a report
uv sync --extra dev
export GEMINI_API_KEY="..." # default provider
export OPENAI_API_KEY="sk-..." # fallback
export ANTHROPIC_API_KEY="sk-..." # optional: --provider claude
uv run python scripts/generate_analysis.py AAPL # fundamental-analysis
uv run python scripts/generate_analysis.py MSFT --analysis-type technical-analysis
uv run python scripts/generate_analysis.py NVDA --analysis-type stock-valuation --provider openai
Output goes to ai_gen_report/fundamental/<ticker>/,
ai_gen_report/technical/<ticker>/ or ai_gen_report/stock/<ticker>/.
Run the tests
uv run pytest tests/ -v # offline, no API keys needed
Build the site locally
uv pip install "mkdocs-material==9.5.*" mkdocs-awesome-pages-plugin minify-html
uv run python scripts/build_docs.py
uv run mkdocs serve
Download SEC filings
uv run python scripts/download_10k_edgar.py AAPL --years 5 # 10-K PDFs from EDGAR
uv run python scripts/download_10q_edgar.py AAPL # 10-Q PDFs from EDGAR
uv run python scripts/download_10k_pdf.py meta-platforms-inc # from annualreports.com
Trigger CI runs
gh workflow run daily_analysis.yml -f ticker=MSFT -f analysis_type=technical-analysis
make analyze TICKERS="NVDA TSLA" TYPES="fundamental-analysis,technical-analysis"
make deep-dive TICKERS="NVDA" # earnings-call, insider, 13F and HTML report
make help # all targets
여기까지가 README 앞부분입니다. 나머지는 원문에서 읽을 수 있습니다. README 전문 보기 ↗
