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 Aug 2026, 19:30 | — | 15.0B | 7.90B | — |
| 17 Aug 2026, 12:30 | 40.83BC$ | 15BC$ | 8.8BC$ | +25.83 |
| 17 Jul 2026, 12:30 | 7.9BC$ | 15.21BC$ | 46.91BC$ | -7.31 |
| 16 Jun 2026, 12:30 | 46.91BC$ | 8.16BC$ | 4.4BC$ | +38.75 |
| 15 May 2026, 12:30 | 4.62BC$ | 11.4BC$ | 5.84BC$ | -6.78 |
| 17 Apr 2026, 12:30 | 6.17BC$ | 23.81BC$ | 46.79BC$ | -17.64 |
| 18 Mar 2026, 12:30 | 46.73BC$ | 4.72BC$ | -5.84BC$ | +42.01 |
| 17 Feb 2026, 13:30 | -5.57BC$ | 14.27BC$ | 15.96BC$ | -19.84 |
| 16 Jan 2026, 13:30 | 16.33BC$ | 24.61BC$ | 46.62BC$ | -8.28 |
| 17 Dec 2025, 13:30 | 46.62BC$ | 21.84BC$ | 31.32BC$ | +24.78 |
| 17 Nov 2025, 13:30 | 31.32BC$ | — | 23.61BC$ | — |
| 17 Oct 2025, 12:30 | 25.92BC$ | 11.61BC$ | 26.66BC$ | +14.31 |
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.