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 |
|---|---|---|---|---|
| 17 Sep 2026, 12:30 | — | — | 1.774M | — |
| 10 Sep 2026, 12:30 | 1.774M | 1790K | 1.775M | -1788.226 |
| 03 Sep 2026, 12:30 | 1.775M | — | 1.771M | — |
| 27 Aug 2026, 12:30 | 1.771M | 1790K | 1.796M | -1788.229 |
| 20 Aug 2026, 12:30 | 1.796M | 1790K | 1.781M | -1788.204 |
| 13 Aug 2026, 12:30 | 1.781M | 1800K | 1.799M | -1798.219 |
| 06 Aug 2026, 12:30 | 1.799M | 1790K | 1.777M | -1788.201 |
| 30 Jul 2026, 12:30 | 1.777M | 1800K | 1.789M | -1798.223 |
| 23 Jul 2026, 12:30 | 1.789M | — | 1.798M | — |
| 16 Jul 2026, 12:30 | 1.798M | 1820K | 1.821M | -1818.202 |
| 09 Jul 2026, 12:30 | 1.821M | 1820K | 1.806M | -1818.179 |
| 02 Jul 2026, 12:30 | 1.806M | 1810K | 1.812M | -1808.194 |
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.