How to read the signals
Early Signal
The day our daily scan first flags a stock in the setup we look for. This is the watchlist stage — the stock may be setting up, nothing more. (This is what "trigger" means — one event, one name: Early Signal.)
Early Candidate
An Early Signal that hasn't confirmed yet. Most never do. Treat these as a watchlist, not a buy list: the scan has flagged them early, and we're waiting to see if they confirm.
Confirmed Signal
Most Early Signals never confirm. A signal is confirmed only when a second, independent pass in the days that follow verifies the turn is actually underway. Only confirmed signals enter the official track record, and every headline statistic on this site is measured from the confirmation.
Everything published on this site — including the signals, statistics, track record, groups, and commentary — is provided for educational and informational purposes only. It is not financial advice, and it is not investment, legal, or tax advice. Nothing here is a recommendation, offer, or solicitation to buy, sell, or hold any security, or to follow any particular investment strategy.
Past performance does not guarantee future results. The track record shown is a historical, rules-based record computed from market and SEC filing data believed to be reliable but not guaranteed as to accuracy or completeness. It is not the performance of any actual investment account, and no representation is made that any person will, or is likely to, achieve similar results. Investing and trading involve substantial risk, including the possible loss of principal.
Always do your own research, and consult a licensed financial advisor or other qualified professional before making any investment decision. By using this site you acknowledge that your investment decisions are your own, and that the publisher accepts no liability for losses or damages arising from the use of this information.
About this record: backfill of 2022-01-04 to 2026-10-22; returns since the Early Signal measured to the 2026-10-23 close, split/dividend adjusted.
Fundamentals and market cap are point-in-time: SEC EDGAR facts as originally filed on or before each signal date; shares outstanding from the closest filing on or before the signal date. The signal log is append-only — a stock admitted at its Early Signal date is never removed, even if it later falls below the size floors.
An Early signal that never confirms within its confirmation window is closed out: it leaves the Current tab, its live figures freeze at closeout, and it moves to the separate never-confirmed list on the Track Record tab, labelled CLOSED — never confirmed. All performance statistics on this page are computed over confirmed signals only (n=12490 of 19555 Early signals), shown from both entries — the Early Signal and the confirmation — because the two decision points are graded separately. Never-confirmed signals feed no statistic.
Signals from different share classes of the same issuer landing close together are counted once in these statistics, and a name that stops trading stays in the record, marked DELISTED.
Category: Quality = passed the screener's point-in-time fundamental health checks at the signal date; Junk = did not, and was admitted on a stricter size basis. The exact category tests are part of the member methodology.
The REVENUE ↑ / REVENUE ↓ marker shows point-in-time TTM revenue growth at the signal date (SEC filings available by then): green when revenue was still growing, red when it was shrinking, absent when it cannot be established point-in-time. It is shown as information, not used as an admission gate.
The WASHOUT / CAPITULATION / EXHAUSTION groups rank Quality signals by the strength of the bottom evidence present at the Early Signal, measured in an October 2026 study of the confirmed cohort: WASHOUT (85% finished positive since the Early Signal vs 63% for all confirmed, mean +38%); CAPITULATION (77%, mean +59%); EXHAUSTION (75%, mean +32% — small sample, early evidence). Groups are mutually exclusive: every confirmed signal sits in exactly one. A ▼ DOWNTREND group replaces any bottom-evidence group for certain repeat Early Signals, identified by a proprietary method. The groups prioritize investigation only — they are not an admission gate, and Junk signals earn none. The evidence tests behind each group are part of the member methodology.
Universe is US exchange-listed stocks only (NASDAQ / NYSE / NYSE American / NYSE Arca / Cboe) — no OTC. Survivorship caveat: the universe is built from current listings, so companies delisted before the backfill do not appear.
The +30/+60/+90-day columns count only signals whose full horizon had elapsed by 2026-10-23; younger signals show —. The full methodology — Early Signal thresholds, confirmation rules, category tests, and group evidence tests — is proprietary. This site is an educational screening tool, not investment advice.
The Screener
Every Early Signal — newest first, grouped by week. 19,555 signals since January 2022; tap a group pill to see only the flagship setups.
Signal groups
Every confirmed signal is checked against the three flagship setups:
Washout — A quality company — using proprietary screening — sold down far below its long-term trend. The business is intact; the price isn't.
Capitulation — A washout where the selling climaxes — volume spiking as the last holders give up, and forced selling burns itself out.
Exhaustion — A washout where the decline itself runs out of sellers — the rarest scenario the screen produces.
A signal that doesn't meet the requirements for any of the three is Uncategorized — select it to see only those stocks.
All four groups start on, showing every signal — tap a group off to hide it, tap again to bring it back.
