Home / Market & alternative data
disclosure-alpha
Deterministic section scores for SEC periodic filings
What it is
An open-source pipeline that scores annual and quarterly US securities filings from the HTML, with no language model in the path. It extracts sections, measures tone and boilerplate, raises risk flags, diffs a filing against the prior one, and serves the same scores from a command line, Python, HTTP, or a Model Context Protocol server. Fundamental analysts who want a repeatable screen can pass a ticker or a local HTML file. Current-report forms are outside the ticker routes, ticker downloads need a declared user agent, and the numbers are text metrics rather than a trading signal.
At a glance
Worth watchingOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Professional quants |
|---|---|
| Used for | Data analysis, Strategy research |
| Markets | US equities |
| Stack | Python |
| Learning curve | Moderate learning curve |
| Practical value | Medium practical value |
| Cost | Free and open source |
| Hardware | No GPU needed |
| Maintenance | Last commit 20 days ago |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): 0 over the period, now 4. Gaps mean no snapshot was taken that day.
Deterministic SEC filing analytics for 10-K/10-Q: section extraction, tone and boilerplate metrics, year-over-year diff, and reproducible disclosure risk scores. CLI, Python SDK, HTTP panel
Similar tools
Python toolkit for statistical and algorithmic portfolio construction
Performance analysis of predictive stock factors
Pairwise fundamental scores for two US stocks
Using LLMs on annual reports to inform stock strategies
Monthly excess-move tables after SEC filings
Transparent Python toolkit of financial metrics and ratios