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 |
|---|---|---|---|---|
| 01 Sep 2026, 14:00 | 71.1 | 72 | 71.1 | -0.9 |
| 03 Aug 2026, 14:00 | 71.1 | 70.3 | 73 | +0.8 |
| 01 Jul 2026, 14:00 | 73 | 79 | 82.1 | -6 |
| 01 Jun 2026, 14:00 | 82.1 | 85.5 | 84.6 | -3.4 |
| 01 May 2026, 14:00 | 84.6 | 80 | 78.3 | +4.6 |
| 01 Apr 2026, 14:00 | 78.3 | 73 | 70.5 | +5.3 |
| 02 Mar 2026, 15:00 | 70.5 | 59.5 | 59 | +11 |
| 02 Feb 2026, 15:00 | 59 | 60.5 | 58.5 | -1.5 |
| 05 Jan 2026, 15:00 | 58.5 | 59 | 58.5 | -0.5 |
| 01 Dec 2025, 15:00 | 58.5 | 59.5 | 58 | -1 |
| 03 Nov 2025, 15:00 | 58 | 61.7 | 61.9 | -3.7 |
| 01 Oct 2025, 14:00 | 61.9 | 63.2 | 63.7 | -1.3 |
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.