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 |
|---|---|---|---|---|
| 16 Sep 2026, 14:30 | — | — | 1.269 | — |
| 10 Sep 2026, 16:00 | 1.269M | -1.4M | -1.173M | +2.669 |
| 02 Sep 2026, 14:30 | -1.173M | -1.9M | -2.536M | +0.727 |
| 26 Aug 2026, 14:30 | -2.536M | -0.7M | 0.688M | -1.836 |
| 19 Aug 2026, 14:30 | 0.688M | -1.2M | -0.968M | +1.888 |
| 12 Aug 2026, 14:30 | -0.968M | -1.2M | -1.643M | +0.232 |
| 05 Aug 2026, 14:30 | -1.643M | -1.3M | 0.007M | -0.343 |
| 29 Jul 2026, 14:30 | 0.007M | -0.7M | 0.765M | +0.707 |
| 22 Jul 2026, 14:30 | 0.765M | -1.54M | -1.533M | +2.305 |
| 15 Jul 2026, 14:30 | -1.533M | -0.8M | -1.904M | -0.733 |
| 08 Jul 2026, 14:30 | -1.904M | -1.6M | -2.333M | -0.304 |
| 01 Jul 2026, 14:30 | -2.333M | -0.95M | 2.064M | -1.383 |
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.