Loading dataset

Description

Screen every US-listed stock and ETF on price trend, risk, balance sheet, SEC fundamentals and what its 10-Ks have said since 2010. The search table joins everything onto one row per listing: price and technicals, the latest SEC income statement, cash flow and balance sheet, valuation, ten years of growth and payout history, filing activity, and what the latest 10-K says the company does, sells and risks.

The dataset holds about 13,200 listings (12,300 in the search table), 226,000 company fiscal periods, 5.2 million SEC filings and 22 million daily price bars in five tables, plus 4,281 latest 10-K reports and 49,107 annual reports since 2010.

Coverage

  • Window: trading days from 4 January 2010 to the latest US close. SEC filings, fundamentals and annual reports since 2010, on US market dates.
  • Grain: one row per ticker in the search, screener, listings and latest-10-K tables. One row per report, per ticker-day, per company-period and per filing in the others.
  • Cadence: quotes, listings, filings and the screener rebuild every weekday evening after the US close. Prices and fundamentals rebuild every Saturday morning. The search table rebuilds whenever one of them does. The 10-K tables are a snapshot of filings to 1 November 2026 and do not refresh on a schedule.
  • Listings: stocks and ETFs on Nasdaq, NYSE, NYSE American, NYSE Arca and Cboe BZX, plus a few dozen listings with an unresolved exchange code.

Columns

  • search_stocks (the main table, 244 columns): identity, exchange, sector, industry and headquarters. Price, returns from 1 day to 10 years, volatility, drawdown, moving averages, RSI, MACD, volume and beta. Revenue, profit, EBITDA, EPS, R&D, cash flow, capex, buybacks and dividends. Cash, investments, debt, net cash, assets, equity and goodwill. Margins, ROE, leverage, P/E, P/S, P/B, EV/EBITDA and yields. Revenue CAGR over 3, 5 and 10 years, profit streaks, filing dates, and the latest 10-K's facts and labels.
  • filings_10k (latest per company) and filings_10k_history (every report since 2010): cover facts, going-concern and material-weakness flags, AI and tariff mentions, Item 1 facts an extraction model read verbatim (description, products, segments, customers, competitors, employees, website) and labels a classification model gave (sector, business model, AI exposure, company type, geography, top risk) with probabilities. The yearly filings_10k_2010 to filings_10k_2026 and source_10k_sections tables are its build stages.
  • series_prices_a_d to series_prices_s_z: daily OHLC, adjusted close and volume with returns, moving averages, MACD, RSI, ATR, volatility and the 52-week range.
  • series_fundamentals and source_fundamentals_latest: the SEC income statement, cash flow and balance sheet lines in US dollars, by fiscal period and as each filer's latest figures.
  • source_quotes_latest, source_filings and source_securities: the latest quote, every SEC filing with its link, and every listing with exchange, type, CIK and SIC code.

Missing values

Missing values are empty cells. Ratios are empty when the denominator is zero or negative, long returns for young listings, and ETFs carry no SEC fundamentals or 10-K. Debt is empty when a filer tags no borrowing concept, so net cash needs both cash and debt. A 10-K fact is empty when Item 1 does not state it. Before 2016 about one report in ten has no Item text, and cover facts exist only from mid-2019. Before June 2024, highs, lows and drawdowns use weekly closes.

Suitable for

  • Screens mixing momentum, valuation, profitability and balance-sheet strength
  • Finding companies by what they do, sell and say about AI or tariffs
  • Tracing a company's business and risks year by year since 2010

Source and rights

Prices and quotes: EODHD end-of-day data under this workspace's subscription. Listings, financial statements, filings and annual reports: SEC EDGAR and its XBRL frames, public records of the US Securities and Exchange Commission.

Tables43

Explore

1
  • Table healthStatus unavailableStock & ETF screenerTable overviewPublished rows12,277Columns245 rows
    Status unavailable

Prices

6

Financials

2

SEC reports

3
  • Table healthStatus unavailableLatest annual report profilesTable overviewPublished rows4,281Columns80 rows
    Status unavailable
  • Table healthStatus unavailableAnnual report historyTable overviewPublished rows49,107Columns80 rows
    Status unavailable
  • Table healthStatus unavailableSEC filing indexTable overviewPublished rows5,256,241Columns13 rows
    Status unavailable

Reference

1
  • Table healthStatus unavailableSecurity directoryTable overviewPublished rows13,244Columns32 rows
    Status unavailable

Build intermediates

30

Sources

ClefServed by Clef (asia-south2), Clef (asia-southeast1), Clef (us-central1) and Clef (europe-west4)6 endpoints
Usage rights
Allowed by terms of service.
Collection
6 requests across 6 endpoints

Collected endpoints

A small classification model reads the first 64,000 characters of each report's Item 1 Business section and labels the sector, customers, revenue model, AI exposure, company type and geographic focus (part 1 of 5).classify_business_11 request
A small classification model reads the first 64,000 characters of each report's Item 1 Business section and labels the sector, customers, revenue model, AI exposure, company type and geographic focus (part 1 of 5).classify_business_21 request
A small classification model reads the first 64,000 characters of each report's Item 1 Business section and labels the sector, customers, revenue model, AI exposure, company type and geographic focus (part 1 of 5).classify_business_31 request
A small classification model reads the first 64,000 characters of each report's Item 1A Risk Factors and labels the theme it stresses most, and whether it names tariffs, AI or going-concern doubt as risks (sections part 1 of 5).classify_risks_11 request
A small classification model reads the first 64,000 characters of each report's Item 1A Risk Factors and labels the theme it stresses most, and whether it names tariffs, AI or going-concern doubt as risks (sections part 1 of 5).classify_risks_21 request
A small classification model reads the first 64,000 characters of each report's Item 1A Risk Factors and labels the theme it stresses most, and whether it names tariffs, AI or going-concern doubt as risks (sections part 1 of 5).classify_risks_31 request
TablePermission asserted.3 endpoints
Usage rights
Permission asserted.
Collection
3 requests across 3 endpoints

Collected endpoints

This dataset's source_10k_sections_2012_1 table: the Items and cover facts of part 1 of 3 of the annual reports filed in 2012.sections_11 request
This dataset's source_10k_sections_2012_2 table: the Items and cover facts of part 2 of 3 of the annual reports filed in 2012.sections_21 request
This dataset's source_10k_sections_2012_3 table: the Items and cover facts of part 3 of 3 of the annual reports filed in 2012.sections_31 request
extractServed by NuExtract3 G (us-central1)3 endpoints
Usage rights
Allowed by terms of service.
Collection
3 requests across 3 endpoints

Collected endpoints

Our extraction model reads the first 64,000 characters of each report's Item 1 Business section and returns the named facts, each one verbatim from the text (sections part 1 of 5).extract_business_11 request
Our extraction model reads the first 64,000 characters of each report's Item 1 Business section and returns the named facts, each one verbatim from the text (sections part 1 of 5).extract_business_21 request
Our extraction model reads the first 64,000 characters of each report's Item 1 Business section and returns the named facts, each one verbatim from the text (sections part 1 of 5).extract_business_31 request

Details

Contents
43 tables · 27,984,675 rows · 2,804 columns
Coverage
–
Category
Finance
Updated
Published
Version
2026-11-06
License
Not stated
Visibility
Public
Publisher
Mostly Right

Activity

Views2,610+2,610 in the last 30 days
Likes0+0 in the last 30 days
Uses386+386 in the last 30 days

Support

Talk to Mostly Right

Loading chat…