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 |
|---|---|---|---|---|
| 18 Aug 2026, 06:00 | -11K | 11.2K | -6.4K | -22.2 |
| 21 Jul 2026, 06:00 | 6.7K | 29.4K | 1.3K | -22.7 |
| 18 Jun 2026, 06:00 | 31.2K | 25.8K | 8.3K | +5.4 |
| 19 May 2026, 06:00 | 26.5K | 27.3K | 4.9K | -0.8 |
| 21 Apr 2026, 06:00 | 26.8K | 21.4K | 17.1K | +5.4 |
| 19 Mar 2026, 07:00 | 24.7K | 25.8K | 4.7K | -1.1 |
| 17 Feb 2026, 07:00 | 28.6K | 22.8K | 2.7K | +5.8 |
| 20 Jan 2026, 07:00 | 17.9K | 15.6K | -3.3K | +2.3 |
| 16 Dec 2025, 07:00 | 20.1K | 22.3K | -3.9K | -2.2 |
| 11 Nov 2025, 07:00 | 29K | 20.3K | 0.4K | +8.7 |
| 14 Oct 2025, 06:00 | 25.8K | 10.3K | -2K | +15.5 |
| 16 Sep 2025, 06:00 | 17.4K | 20.3K | -33.3K | -2.9 |
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.