How often the band holds

D+1 and D+2 are not the same thing

D+1 is produced after tomorrow's auction closes — the day-ahead price is already set, so it is validation, not a decision. D+2 is issued while the auction for the day after tomorrow has not been held yet: it is the prediction you actually operate on. When the two diverge, D+2 is the figure that matters, and it is the harder one to hit.

What does not hold yet

The D+2 band covers below the 80% target on Bulgaria (BG), 64.5% and Romania (RO), 70.0%. That means precisely that it is too narrow on the horizon we operate on: anyone sizing risk on P10–P90 at D+2 underestimates the tail. We are widening it, even though the figure will look less impressive — a band that holds less than it claims is worse than a visibly wider one.

Coverage, month by month

The whole scored history, with no periods removed. February 2026 is on the chart exactly like July: publish only the good months and you have not published a track record.

Frozen forecasts

Every row here was frozen in the database before the answer was known, then scored once the realised price arrived. Nobody can touch them any more — not even us. This is the evidence the page stands on.

Series marked “thin sample” have fewer than 60 scored days. We publish them because they exist, not because they support a conclusion.

Validation, not forecast

The same days, but the forecast was issued in the evening, after the auction closed — when the next day's price was already published. It could not be traded on, and we do not call it a forecast. It is useful to know how well the model reads a day it already almost has in front of it, but that is a question about the model, not an instrument.

And how it would have behaved over history

A reconstruction: for each past day, a model trained strictly on the days before it, compared against the realised price. It is causal, therefore legitimate — but it remains a backtest, run today, with today's code, and recomputable at will. That is why it sits apart: it is a different kind of evidence, not the same measurement over more days. It does not compare row by row with the table above, because the periods do not overlap: the reconstruction covers months the frozen forecast has not reached yet — including February 2026, the worst month in the whole record. We publish it precisely because that month is in it.

How it is measured

• The truth is the day-ahead price as reported on the ENTSO-E Transparency Platform, in each market's own currency; for Romania, converted to RON at the official National Bank of Romania rate. We do not compare a forecast against another forecast.
• Coverage is the fraction of 15-minute intervals where the realised price fell between P10 and P90. The target, by construction, is 80%.
• rMAE is the mean absolute error on P50, relative to the day's mean realised price. A high rMAE in a low-price month is not necessarily a bad month.
• The model re-trains from scratch every day, with no accumulated weights. There is no moment at which “the model was calibrated”; there is only how it behaves, day after day.