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 |
|---|---|---|---|---|
| 27 Aug 2026, 12:30 | -118.8B$ | -99B$ | -101.41B$ | -19.8 |
| 28 Jul 2026, 12:30 | -101.5B$ | -100B$ | -105.89B$ | -1.5 |
| 26 Jun 2026, 12:30 | -105.8B$ | -85B$ | -83.01B$ | -20.8 |
| 29 May 2026, 12:30 | -82.4B$ | -86.5B$ | -85.3B$ | +4.1 |
| 29 Apr 2026, 12:30 | -87.87B$ | -87B$ | -83.5B$ | -0.87 |
| 19 Feb 2026, 13:30 | -98.5B$ | -86B$ | -82.8B$ | -12.5 |
| 29 Dec 2025, 13:30 | — | — | — | — |
| 29 Oct 2025, 12:30 | -79B$ | -90B$ | -85.6B$ | +11 |
| 25 Sep 2025, 12:30 | -85.5B$ | -95.65B$ | -102.8B$ | +10.15 |
| 29 Aug 2025, 12:30 | -103.6B$ | -89.5B$ | -84.85B$ | -14.1 |
| 29 Jul 2025, 12:30 | -85.99B$ | -98.4B$ | -96.42B$ | +12.41 |
| 26 Jun 2025, 12:30 | -96.59B$ | -88.5B$ | -86.97B$ | -8.09 |
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.