Ponzi methodology →
EDGAR forms: Form D
recall 35% precision 15% + content rule precision 0%
Crypto / Digital-Asset Securities methodology →
EDGAR forms: 1-A · S-1 · 8-K
recall 43% precision 2%
Cyber Fraud methodology →
No EDGAR filing fingerprint — criminal/DOJ-side scheme, detected from case text.
Market Manipulation methodology →
EDGAR forms: SC 13D/G · 13F
recall 53% precision 9% + content rule precision 11%
Insider Trading methodology →
EDGAR forms: 4 · 3 · 5 · 144 · 8-K · 10-Q
recall 81% precision 19%
active development — services may be restarted or go down without notice and data is regenerated frequently. Do not rely on any data or service here. Nothing on this site is legal, financial, or investment advice.

Securities Anomalies

Full Corpus Statistics 4,152
SEC/DOJ Heuristics

4,152 documents, 3 sources, 1198.8MB, 1995–2026. Filtered to securities-fraud signals (pump-dump · unregistered · ticker · manipulation · reverse-merger · boiler-room · shell · microcap · penny-stock · insider).

All 9,614 insider-trading 2,591 unregistered-securities 1,828 pump-and-dump 1,004 ponzi 759 market-manipulation 675 accounting-fraud 582 financial-fraud 498 investment-adviser-fraud 348 non-corporate 260 broker-dealer-fraud 249 pre-ipo-fraud 168 boiler-room 167 corporate-fraud 139 crypto-securities 110 affinity-fraud 52 health-care-fraud 49 fcpa 33 obstruction 30 public-corruption 27 advance-fee 25 cyber-fraud 17 racketeering 3
Selected scheme types: insider-trading, ponzi, market-manipulation, crypto-securities, cyber-fraud contains 4,152 documents clear
SEC 3,820 docs
SEC Litigation Releases / complaint 789 | 1995–2026 | 699.9MB
SEC Litigation Releases / judgment 34 | 2003–2026 | 18.5MB
SEC Litigation Releases / litigation release 2,163 | 1995–2026 | 138.3MB
SEC Press Releases / complaint 273 | 2006–2026 | 274.2MB
SEC Press Releases / press release 561 | 1997–2026 | 25.5MB
DOJ 332 docs
DOJ SDNY / indictment 6 | 2013–2024 | 3.9MB
DOJ SDNY / press release 326 | 2013–2026 | 38.5MB
build b23a6a8 · corpus snapshot pinned to this build