Daily guide · IT-CNOR · 2026-08-30
The number your Italy Centre-North price model has to beat this week
All numbers computed from the week's published auction results at publication and frozen — this article is an honest snapshot, not a page that rewrites itself. Reproduce via the API.
The number to beat this week is 24,15 EUR/MWh, the persistence baseline's mean absolute error across the six days. That figure is inflated by a single day: 24 August, where persistence missed by 65,44 EUR/MWh against a day mean of 192,58. Strip that outlier and the baseline looks far tighter, with four of the remaining five days between 9,14 and 18,44 EUR/MWh.
For a quant, that split matters. The mid-week stretch of 27 and 28 August, with persistence MAE of 11,32 and 9,14 against day means near 204 and 206, is a low-volatility regime where yesterday's price is hard to improve on. The edge sits at the edges: 24 August, and to a lesser degree 29 August at 25,61.
The concrete takeaway is to accept you will not out-forecast persistence on the calm mid-week days, and concentrate model effort on the transition days. Over the trailing window our own model runs at 19,51 EUR/MWh versus a 22,31 baseline across 334 days, so beating 24,15 this week is realistic, provided the 24 August type of break is captured.
Before you train anything on IT-CNOR prices, you need the number your model has to beat. In day-ahead forecasting that number is naive persistence: predict that tomorrow's curve equals today's. It costs nothing, needs no features, and it is embarrassingly hard to beat — because power prices are dominated by daily and weekly rhythms that persistence gets for free. We computed it on this exact week:
24.15 €/MWh
persistence MAE on this week's IT-CNOR auctions — the bar. A model that can't get under this adds negative value.
19.51 vs 22.31
our live production model vs its persistence baseline, trailing 334 scored days — the same scoring, in public, on /accuracy
Why the bar moves: this week, day by day
| Target day | Day mean €/MWh | Persistence MAE |
|---|---|---|
| 2026-08-24 | 192.58 | 65.44 |
| 2026-08-25 | 189.11 | 14.97 |
| 2026-08-26 | 197.35 | 18.44 |
| 2026-08-27 | 204.01 | 11.32 |
| 2026-08-28 | 206.08 | 9.14 |
| 2026-08-29 | 190.99 | 25.61 |
Calm days make persistence look unbeatable; transition days (weather swings, weekend boundaries) are where a real model earns its keep. Averages hide this — always look at the daily distribution.
The part everyone gets wrong: the features
The model is the easy half. The silent killer is lookahead: training on weather reanalysis instead of the forecast that existed at issue time, on revised load data, on same-day flow averages that hadn't finished flowing at the auction. Backtests built that way look brilliant and die in production. Our Quant feature matrices serve one row per (issue day, 15-minute slot) where every column is documented with when it became knowable — the same rows our own models train on:
curl -H "Authorization: Bearer YOUR_KEY" \
"https://voltcast.com/api/v1/features/IT-CNOR?issue_from=2026-07-01&horizons=1"
# columns include: price lags · previous-run weather (as forecast AT issue)
# · grid drivers (lagged to last COMPLETE day) · day-ahead load/RES forecasts
# · ensemble spread · target_price label (null until matured, never imputed)
Start with Home: the persistence bar above needs nothing but GET /v1/prices/IT-CNOR
(Home covers one zone of your choice). When your walk-forward backtest beats it honestly, prove it in public on the
Forecast Bench — forward-blind, open scoring code, and our
own model is auto-entered under identical rules. If you'd rather buy the plumbing than build it,
contact us about ML-grade data access.
Method & citation. Prices are hourly means of published day-ahead auction results (native 15-minute periods averaged; ENTSO-E/SMARD, attributed). Wholesale-price component only — grid fees and taxes come on top and vary by supplier. Cite as "Voltcast Research, voltcast.com/guides/quant-features-it-cnor-2026-08-30".
The monthly European power roundup
Negative-price records, the biggest spreads, which zones were hardest to forecast — every number computed from our production data, on the 2nd of each month. No filler, unsubscribe anytime.