Methodology & Data Sources
Last updated: July 1, 2026
New here? Start with the quick guide →
1. Overview
SpeedSignal scans 3,000+ US equities daily across configured Russell, S&P 500, and Nasdaq 100 universes shortly after the close and assigns each ticker a phase (Coiling, Pre-Ignition, Liftoff or Below) plus a 0–100 score and a Conviction level (Low / Medium / High). Higher scores combined with higher Conviction mean more of the screening conditions are met.
Our scoring is algorithmic and rules-based. It does not use AI predictions, sentiment analysis, or subjective judgment. Given the same market data, every score is reproducible.
2. The Three Pillars
Each pillar is scored from 0 to 100 based on how many of its conditions are present. The three pillars then combine into a single 0–100 score.
Pillar 1: Base "Stealth Coil"
Describes how orderly and compressed a stock's recent trading behavior is:
- Volatility Contraction: how much the stock's day-to-day price swings have tightened versus its own recent history. Tighter compression scores higher.
- Tightness: how narrow and controlled the recent trading action is.
- Squeeze Detection: whether recent volatility compression is notable enough to support a tighter, more orderly setup classification.
- Trend Quality: whether the stock is trending up in an orderly way rather than downtrending or chopping sideways.
- Pivot Proximity: how close the stock is to a relevant technical reference area identified by the methodology.
Pillar 2: Accumulation "Demand Profile"
Surfaces price and volume behavior often associated with persistent participation:
- Relative Strength: whether the stock is leading the broad market rather than lagging it.
- Money Flow: whether volume and price behavior fit sustained-participation patterns rather than a one-day spike.
- Volume Dry-Up: quiet volume while price holds tight, a pattern historically associated with reduced selling pressure.
- Sector Tailwind: whether the broader industry group is supportive rather than acting as a headwind.
Pillar 3: Ignition "Participation Expansion"
Measures whether current price and participation behavior is broadening versus the recent baseline:
- Volume Impulse: whether trading activity is expanding materially versus the stock's normal baseline.
- Early Ignition: whether price and participation are strengthening in the current data.
- Candle Quality: whether the session's price action shows broad-participation characteristics rather than thin or one-sided trading.
3. Phase Classification
| Phase | Meaning |
|---|
| Coiling | Compressed volatility and tight price action that meet the methodology's base-formation criteria. |
| Pre-Ignition | Momentum and accumulation conditions visible in the data. Earlier-stage candidates. |
| Liftoff | Strongest active phase. Price and participation conditions are most aligned in the data for this screening methodology. |
| Below | Not in any active setup phase right now. |
4. Conviction Level
Inside each phase, we add a Conviction dimension: Low, Medium, or High. Conviction reflects how a ticker's score ranks against the rest of the market in that session; High Conviction is reserved for the highest relative scores of the day. It is a separate axis from phase: a Coiling ticker can be High Conviction, and a Liftoff ticker can be Low Conviction.
5. Risk Flags & Anomalies (informational)
Some tickers carry context flags that do not change the score itself but signal risk worth knowing:
- Extended: the stock is already far from its recent base, so the board marks it as extended context.
- Bearish Market Regime: the broad market itself is trending down, a headwind for new breakouts.
- Elevated VIX: market-wide volatility is running high.
- Pre-Earnings Run: a known earnings event is near (event risk).
- Momentum-Only / Anomaly: Moves outside the canonical setup (visible in the Anomalies tab).
6. Eligibility Filters
Before scoring, stocks must pass a set of coverage filters so the board focuses on tradable US equities. The values below are the defaults; most can be adjusted in the Signal Board filters.
- Price ≥ $2
- Liquidity: a minimum average daily dollar-volume
- Market Cap ≥ $300M
- Free Float > 30%
- Not in a clearly established downtrend
- No excessive gap down
- Earnings buffer: scoring paused within a window around confirmed earnings dates, to reduce event-driven noise
7. Data Sources
| Data Type | Source | Update Frequency |
|---|
| Price & Volume | Exchange data via TradingView | Daily at close |
| Fundamentals | FactSet via TradingView | Quarterly |
| Earnings Dates | Exchange filings | As filed |
| Market Context | SPY, VIX, and sector benchmark ETFs | Daily |
| Company Info | syminfo (TradingView) | Static |
8. Limitations
- Scores reflect end-of-day data; intraday moves are not captured
- Historical scores may differ from live scores due to data revisions
- Earnings data availability varies by ticker
- Small-cap stocks can behave differently from larger companies; the board treats that context separately where relevant
- The system is optimized for daily timeframe breakout detection
9. Disclaimer
This methodology description is provided for transparency and educational purposes. Speed Signal AI is screening and analytics software, not a broker-dealer or investment adviser. Scores, phases, and screening results are data outputs and research candidates, not investment advice, recommendations, trading signals, or a buy list. Past performance of high-scoring stocks does not guarantee future results. Always conduct your own research and consult a qualified financial advisor.