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 |
|---|---|---|---|---|
| 03 Sep 2026, 12:30 | -88.58B | -86.4B$ | -71.18B | -2.18 |
| 04 Aug 2026, 12:30 | -71.18B | -73B$ | -75.75B | +1.82 |
| 07 Jul 2026, 12:30 | -75.75B | -78.5B$ | -52.88B | +2.75 |
| 09 Jun 2026, 12:30 | -52.88B | -56.1B$ | -53.66B | +3.22 |
| 05 May 2026, 12:30 | -56.58B | -60.9B$ | -54.98B | +4.32 |
| 02 Apr 2026, 12:30 | -57.3B$ | -59.2B$ | -54.7B$ | +1.9 |
| 12 Mar 2026, 12:30 | -54.5B$ | -66.6B$ | -72.9B$ | +12.1 |
| 19 Feb 2026, 13:30 | -70.3B$ | -55.5B$ | -53B$ | -14.8 |
| 29 Jan 2026, 13:30 | -56.8B$ | -40.5B$ | -29.2B$ | -16.3 |
| 08 Jan 2026, 13:30 | -29.4B$ | -58.9B$ | -48.1B$ | +29.5 |
| 11 Dec 2025, 13:30 | -52.8B$ | -63.3B$ | -59.3B$ | +10.5 |
| 19 Nov 2025, 13:30 | -59.6B$ | -61B$ | -78.2B$ | +1.4 |
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.