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, 12:30 | 1.443M | 1.37M | 1.374M | +0.073 |
| 17 Jul 2026, 12:30 | 1.367M | 1.4M | 1.41M | -0.033 |
| 16 Jun 2026, 12:30 | 1.413M | 1.42M | 1.423M | -0.007 |
| 21 May 2026, 12:30 | 1.442M | 1.39M | 1.363M | +0.052 |
| 29 Apr 2026, 12:30 | 1.372M | 1.39M | 1.538M | -0.018 |
| 12 Mar 2026, 12:30 | 1.376M | 1.41M | 1.455M | -0.034 |
| 18 Feb 2026, 13:30 | 1.448M | 1.4M | 1.388M | +0.048 |
| 09 Jan 2026, 13:30 | 1.412M | 1.35M | 1.415M | +0.062 |
| 17 Sep 2025, 12:30 | 1.312M | 1.37M | 1.362M | -0.058 |
| 19 Aug 2025, 12:30 | 1.354M | 1.39M | 1.393M | -0.036 |
| 18 Jul 2025, 12:30 | 1.397M | 1.39M | 1.394M | +0.007 |
| 18 Jun 2025, 12:30 | 1.393M | 1.43M | 1.422M | -0.037 |
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.