A scheduled macroeconomic release. Prints that miss their forecast tend to move related markets sharply in the minutes around the release, which is why a validation run that straddles the window is hard to compare with a backtest that never saw it.
| Date (UTC) | Actual | Forecast | Previous | Surprise |
|---|---|---|---|---|
| 10 Sep 2026, 16:00 | -0.391M | -1.6M | -4.45M | +1.209 |
| 02 Sep 2026, 14:30 | -4.45M | -1.1M | 0.095M | -3.35 |
| 26 Aug 2026, 14:30 | 0.095M | 0.6M | 4.405M | -0.505 |
| 19 Aug 2026, 14:30 | 4.405M | -0.6M | 17.422M | +5.005 |
| 12 Aug 2026, 14:30 | 17.422M | -1.4M | 2.479M | +18.822 |
| 05 Aug 2026, 14:30 | 2.479M | -1.5M | -7.167M | +3.979 |
| 29 Jul 2026, 14:30 | -7.167M | -1.3M | 2.011M | -5.867 |
| 22 Jul 2026, 14:30 | 2.011M | -1.25M | -1.693M | +3.261 |
| 15 Jul 2026, 14:30 | -1.693M | -2.6M | 2.998M | +0.907 |
| 08 Jul 2026, 14:30 | 2.998M | -2.4M | -3.775M | +5.398 |
| 01 Jul 2026, 14:30 | -3.775M | -5.1M | -6.088M | +1.325 |
| 24 Jun 2026, 14:30 | -6.088M | -4.5M | -8.263M | -1.588 |
Surprise is actual minus forecast, in the indicator's own units. It is what happened, not a prediction.
Spreads widen and fills slip in the minutes around a scheduled release, which distorts a validation run's entry prices. Treat forward results that straddle this window with care — they are not comparable to a backtest that never saw it.
High-impact releases are posted to the channel 15 minutes ahead, and again with the actual figure once it prints.