foxalgoBias
We do not sell a directional prediction. Below is what the measured data actually says about "up" vs. "down" — and, separately, three specific directional edges we went looking for and did not find. As of 16:26 ET.
Descriptive statistics, not signals — touching a level is not earning money on it. Every number on this page ships with its sample size (n) and confidence interval. See methodology.
What the data does say about direction
For each market: P(touch 0.5 ATR up) vs. P(touch 0.5 ATR down) from right now, the difference in percentage points, and the sample size behind it.
The asymmetry you see below comes from position in today's range and time remaining in the session — not from a directional forecast. When price sits near today's low, P(up) exceeds P(dn) simply because there is more room to travel upward than downward before the level is reached; that is geometry, the same geometry a coin flip would show if you nailed it to a bounded range. It is not an opinion about where price is headed next.
Futures
| market | P(touch UP 0.5 ATR) | P(touch DOWN 0.5 ATR) | diff (pp) | n | position in range |
|---|---|---|---|---|---|
| E-mini S&P 500 | 25.1% | 28.9% | -3.9 pp | 11,654 | not cached yet |
| E-mini Nasdaq 100 | 25.1% | 28.9% | -3.9 pp | 11,654 | not cached yet |
| E-mini Dow | 25.1% | 28.9% | -3.9 pp | 11,654 | not cached yet |
| E-mini Russell 2000 | 25.1% | 28.9% | -3.9 pp | 11,654 | not cached yet |
| Gold | 29.2% | 29.9% | -0.7 pp | 9,626 | not cached yet |
| WTI Crude | 26.9% | 30.1% | -3.2 pp | 9,575 | not cached yet |
P(touch by close) — horizon convention follows each symbol's detail page.
FX
| market | P(touch UP 0.5 ATR) | P(touch DOWN 0.5 ATR) | diff (pp) | n | position in range |
|---|---|---|---|---|---|
| EUR/USD | 40.3% | 39.6% | +0.7 pp | 8,516 | 70% of today's range |
| GBP/USD | 40.3% | 39.6% | +0.7 pp | 8,516 | 61% of today's range |
| USD/JPY | 40.3% | 39.6% | +0.7 pp | 8,516 | 74% of today's range |
| AUD/USD | 40.3% | 39.6% | +0.7 pp | 8,516 | 84% of today's range |
| USD/CAD | 40.3% | 39.6% | +0.7 pp | 8,516 | 20% of today's range |
| USD/CHF | 40.3% | 39.6% | +0.7 pp | 8,516 | 66% of today's range |
| NZD/USD | 40.3% | 39.6% | +0.7 pp | 8,516 | 81% of today's range |
| Gold spot (XAU/USD) | 40.3% | 39.6% | +0.7 pp | 8,516 | not cached yet |
P(touch within next 1440m) — horizon convention follows each symbol's detail page.
Stocks
| market | P(touch UP 0.5 ATR) | P(touch DOWN 0.5 ATR) | diff (pp) | n | position in range |
|---|---|---|---|---|---|
| S&P 500 ETF (SPY) | 1.2% | 1.9% | -0.7 pp | 1,861 | 27% of today's range |
| Nasdaq 100 ETF (QQQ) | 1.2% | 1.9% | -0.7 pp | 1,861 | 45% of today's range |
| Russell 2000 ETF (IWM) | 1.2% | 1.9% | -0.7 pp | 1,861 | 96% of today's range |
| Apple | 1.0% | 1.1% | -0.2 pp | 4,354 | 51% of today's range |
| Microsoft | 1.0% | 1.1% | -0.2 pp | 4,354 | 24% of today's range |
| Nvidia | 1.0% | 1.1% | -0.2 pp | 4,354 | 22% of today's range |
| Amazon | 1.0% | 1.1% | -0.2 pp | 4,354 | 7% of today's range |
| Alphabet (GOOGL) | 1.0% | 1.1% | -0.2 pp | 4,354 | 24% of today's range |
| Meta Platforms | 1.0% | 1.1% | -0.2 pp | 4,354 | 4% of today's range |
| Tesla | 0.6% | 0.6% | +0.0 pp | 1,152 | 44% of today's range |
| AMD | 0.6% | 0.6% | +0.0 pp | 1,152 | 99% of today's range |
| Netflix | 0.6% | 0.6% | +0.0 pp | 1,152 | 41% of today's range |
P(touch by close 16:00 ET) — horizon convention follows each symbol's detail page.
Historical period 2020-2026, these 12 names selected ex-post (survivorship) — calibration applies to these names, not a random stock. Live frozen scorecard accumulates from launch.
Directional edge we looked for and did not find
Three separate research passes tried to turn something in the data into a genuine directional signal. Here is what happened to each, with the number attached.
Timeframe agreement predicts size, not direction
Tested whether multiple timeframes pointing the same way predicts which way price goes next. Across 242,000 board-states, direction accuracy was 49% — a coin flip. Agreement tracks how big the next move is likely to be, not which way it goes.
Vendor selection predicts resolution, not direction
Tested whether the subset of ranges a market-data vendor chooses to publish carries directional information. Selected and unselected ranges have an identical gambler's-ruin baseline (0.813 vs. 0.807) — yet selected ranges resolve 15 percentage points better. The vendor is picking ranges that resolve cleanly, not ranges that go a particular direction.
Expansion as a directional signal — the effect was a bug
Raw backtest showed range expansion predicting direction with a +18.4 pp edge. After removing an intrabar lookahead bug, the edge fell to +0.2 pp — the entire effect was the bug, not the signal.
If we find a directional edge that survives our own adversarial review, it will appear here with its sample size. Until then, this section stays empty on purpose. See the graveyard for findings we tested and killed, and the methodology for how review works.
Free daily map
Get every tracked market's touch probabilities, every morning, before the open.