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 |
|---|---|---|---|---|
| 15 Sep 2026, 20:30 | — | — | -0.3 | — |
| 09 Sep 2026, 21:00 | -0.3M | -1.3M | -2.6M | +1 |
| 09 Sep 2026, 20:30 | — | -1.3M | -2.6M | — |
| 01 Sep 2026, 20:50 | -2.6M | -0.8M | 4.2M | -1.8 |
| 01 Sep 2026, 20:30 | -2.6M | -0.8M | 4.2M | -1.8 |
| 25 Aug 2026, 22:00 | 4.2M | 1.8M | -0.328M | +2.4 |
| 25 Aug 2026, 20:30 | 4.2M | 1.8M | -0.328M | +2.4 |
| 18 Aug 2026, 21:00 | -3.28M | — | 9.072M | — |
| 18 Aug 2026, 20:30 | -3.28M | — | 9.072M | — |
| 11 Aug 2026, 20:30 | 9.072M | -0.5M | 2.69M | +9.572 |
| 04 Aug 2026, 20:30 | 2.69M | -2M | 3.296M | +4.69 |
| 28 Jul 2026, 20:50 | 3.296M | -2.5M | 2.603M | +5.796 |
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.