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 |
|---|---|---|---|---|
| 19 Aug 2026, 08:00 | 35.1B€ | 22.1B€ | 25.8B€ | +13 |
| 17 Jul 2026, 08:00 | 25.1B€ | 18.1B€ | 17.5B€ | +7 |
| 18 Jun 2026, 08:00 | 15.7B€ | 18.5B€ | 14.9B€ | -2.8 |
| 21 May 2026, 08:00 | 14.9B€ | 25.3B€ | 25.6B€ | -10.4 |
| 17 Apr 2026, 08:00 | 25B€ | 29.8B€ | 40.4B€ | -4.8 |
| 20 Mar 2026, 09:00 | 37.9B€ | 17.2B€ | 13.3B€ | +20.7 |
| 19 Feb 2026, 09:00 | 14.6B€ | 9.2B€ | 8.9B€ | +5.4 |
| 20 Jan 2026, 09:00 | 8.6B€ | 20.3B€ | 26.7B€ | -11.7 |
| 19 Dec 2025, 09:00 | 25.7B€ | 19.6B€ | 23.1B€ | +6.1 |
| 19 Nov 2025, 09:00 | 23.1B€ | 14.5B€ | 22.2B€ | +8.6 |
| 20 Oct 2025, 08:00 | 11.9B€ | 22.5B€ | 29.8B€ | -10.6 |
| 18 Sep 2025, 08:00 | 27.7B€ | 34.6B€ | 35.8B€ | -6.9 |
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.