The whole track record.
Every slice, including misses.
Every prediction — across all markets — scored on the real close-to-close move, broken down by horizon, confidence, sector, region, model and regime. Calibration, risk-adjusted returns and platform discipline included. No cherry-picking.
95% confidence interval: 51.6%–52.6% · All markets
The trust funnel
From every attempt to the calls we scored — nothing hidden, every stage counted.
Accuracy over time
Rolling 7-day directional accuracy vs the 50% coin-flip line — All markets.
By horizon
Bullish vs bearish
Walk-forward accuracy
Accuracy on the most recent N days only — is recent live performance holding up?
Does confidence mean anything?
Actual hit-rate by the model’s own confidence bucket — higher confidence should mean higher accuracy.
| Confidence | Predictions | Actual accuracy | Gap |
|---|---|---|---|
| Low (50-60%) | 5,176 | 46.5% | +8.5pp |
| Medium (60-70%) | 17,214 | 50.0% | +15.1pp |
| High (70-80%) | 6,860 | 55.8% | +19.2pp |
| Very High (80-90%) | 301 | 52.2% | +32.8pp |
| Extreme (90%+) | 7,423 | 57.5% | +38.0pp |
Risk-adjusted returns
Measured on the disciplined book — the signals we actually commit to after the confidence gate, not every raw signal. This is the money-weighted edge.
Returns by horizon (holding-period)
How a user actually experiences it: hold from the call to its horizon. Sharpe here is annualized the correct way — per-trade × √(252 / horizon-days), not a calendar-year compound.
| Horizon | n | Avg hold return | Sharpe (holding-period) | Win rate |
|---|---|---|---|---|
| 1d | 19,662 | -0.033% | -0.14 | 36.6% |
| 5d | 19,054 | +0.294% | 0.31 | 46.0% |
| 7d | 15,427 | +0.479% | 0.44 | 46.8% |
| 10d | 12,368 | +0.768% | 0.44 | 49.4% |
| 15d | 10,981 | +0.449% | 0.20 | 50.0% |
| 20d | 10,561 | +0.002% | 0.00 | 45.4% |
| 25d | 8,255 | -0.899% | -0.26 | 42.6% |
| 30d | 2,651 | -0.414% | -0.12 | 44.5% |
Trade funnel
By asset class
By region
By sector
By model
By market regime
volatility · trendBest tracked
Worst tracked
— shown honestlyDiscipline & coverage
We only commit to a call when confident — and abstain on the rest. Coverage is deliberately low; precision is the point.
How we measure
Directional
Right if the price moves the way we said by the horizon. Unambiguous, checkable.
Close-to-close
Official closes at the horizon date — not intraday ticks we could pick to flatter.
No look-ahead
Locked before the outcome window opens. Out-of-sample, every time.
Calibrated
Each call ships a probability, measured to actually track hit-rate.
The record is the proof. Now see the picks.
Today’s high-conviction calls for Commodities.