AlphaSMO is a financial data newsroom that turns SEC and congressional filings into clear, sourced coverage — so you don't have to dig through EDGAR or government disclosure systems yourself to see what institutions, company insiders, and lawmakers are really doing. We track 13F institutional holdings across 13,000+ funds, Form 4 insider trades, and STOCK Act congressional trading disclosures, and turn them into readable rankings, trend charts, and data-driven narrative summaries — including our own "Smart Money Convergence" signal, which flags when institutions and insiders are buying the same stock at the same time. Every time new filings land, we recompute and republish the numbers — so readers can follow what the big money, and Washington, are doing, sourced directly from the primary filing.
All of our data comes directly from primary government filing systems — the U.S. Securities and Exchange Commission's (SEC) EDGAR system for institutional Form 13F holdings reports, Form 4 insider trading disclosures, Form 144 proposed sale notices, 13D/13G beneficial ownership filings, and 8-K material event disclosures; and the U.S. Senate's Electronic Financial Disclosure (eFD) system for STOCK Act Periodic Transaction Reports filed by Senators. Raw filings are parsed, cleaned, and aggregated by our own data pipeline: 13F holdings are summarized per institution and per stock to compute quarter-over-quarter changes, buy/sell activity, and concentration metrics; insider and congressional trades are aggregated into leaderboards and cluster alerts. Some pages also include AI-generated narrative summaries to help readers quickly understand the story behind the numbers — but every underlying figure traces back to a specific, citeable filing. Update frequency depends on the filing type and its legal disclosure deadline: 13F institutional holdings update quarterly (the SEC gives institutions up to 45 days after quarter-end to file); Form 4 insider trades, Form 144, 13D/13G, and 8-K update daily; STOCK Act congressional disclosures update daily but, by law, can themselves lag the underlying trade by up to 45 days — we display that lag explicitly rather than implying real-time coverage.
AlphaSMO combines a self-built pipeline for ingesting SEC and congressional filing data with natural-language-processing (NLP) automation for drafting narrative content. Our systems pull official filing documents — including SEC Form 4 filings and Senate STOCK Act Periodic Transaction Reports — on a regular, systematic schedule; an automated research pipeline handles the initial structured data cleanup and drafts each narrative summary, and every draft is reviewed by our team before it's published. This lets readers get to the story faster than manually parsing raw filings — while we're explicit about each filing type's own legal disclosure lag (for example, congressional trade reports can legally take up to 45 days to be filed), so nothing on this site is presented as a real-time trading signal.
Prefer to work with the raw data yourself? Download our raw EDGAR-derived 13F datasets on Kaggle, Hugging Face, or Zenodo, updated each quarter.
Our data processing tools and API examples are open source — we believe in technical transparency. Verify our methodology, contribute improvements, or integrate our tools into your workflow: View AlphaSMO on GitHub.
AlphaSMO is founded and built by James, a professional investor and data scientist, combining backgrounds in financial data analysis, data engineering, and full-stack development with a newsroom-style publishing process. We've spent years working with SEC filings, government disclosure systems, and financial analytics — and built AlphaSMO because we wanted primary-source financial reporting that connects 13F filings, insider trades, and congressional disclosures in one place, instead of scattered across a dozen government websites. Our team has direct experience building financial data systems at scale, including institutional-grade data pipelines that process millions of filings. We believe that high-quality, sourced financial reporting should be accessible to individual investors — not just institutions with Bloomberg terminals. For media inquiries, speaking engagements, or partnership opportunities, reach us at contact@alphasmo.com.
AlphaSMO generates two kinds of content: 1. Data-derived content — Rankings, charts, KPIs, and historical trends computed directly from parsed SEC filing data. These are deterministic: any given set of filings always produces the same numbers. 2. AI-generated narrative summaries — Certain pages include commentary produced by a local large language model (currently Gemma 4 via Ollama) that reads the structured data and produces a plain-language summary. The AI has no access to any data beyond what the page already displays, and it does not predict future prices or make buy/sell recommendations. All AI-generated content is explicitly labeled as such with a disclaimer. Every AI-generated narrative is grounded in real, citeable SEC filing data. We do not train our models on user data, and no user data leaves the server. We do not accept sponsored content, paid placements, or compensation for coverage of any stock or institution. The data we present is unfiltered — whether a fund is increasing or decreasing a position, the change is reported as-is.
We take data accuracy seriously. Our automated pipeline runs through multiple validation stages: raw filing parsing is cross-checked against expected schemas, outlier values are flagged for review, and quarter-over-quarter changes are sanity-checked against historical patterns. Despite these safeguards, errors can occur — particularly in the SEC's own raw filing data (e.g., amended filings, restated values, or filing errors by the filer). If you believe you've found an error in our data: - Note the ticker, institution, and specific data point - Reference the source SEC filing if possible (we provide direct links to source filings on every page) - Contact us at contact@alphasmo.com We investigate every reported issue and correct validated errors promptly. Data corrections are reflected on the next data refresh cycle.
For partnership inquiries, API access, or media requests, reach us at contact@alphasmo.com. For technical or account support, visit our contact page.