ETA accuracy benchmark · 🇫🇷 Dunkerque

How Port Flow's predicted ETA compares to each vessel's own broadcast ETA at Dunkerque, measured on closed voyages over the last 7 days. We publish the number — good or bad. Lower error is better.

Port Flow predicted ETA (RMSE)

421.94 h

MAE 181.28 h · 11 voyages

Broadcast ETA (RMSE)

Building…

only 1 comparable voyages so far (need 20)

Gap

—

benchmark builds as more voyages close

Closed voyages

error = predicted/broadcast minus actual arrival (hours)


538004750	container	08/26, 11:36 PM UTC	-0.67 h	-1784.61 h
215231000	container	08/26, 08:45 PM UTC	-0.22 h	—
538007272	container	08/26, 07:53 PM UTC	0.80 h	116.60 h
215231000	container	08/26, 07:45 PM UTC	-0.94 h	—
636024984	product	08/26, 07:39 PM UTC	-12.50 h	—
636023293	container	08/26, 04:40 AM UTC	-1207.59 h	-1196.67 h
255915695	container	08/25, 07:34 PM UTC	-12.33 h	-1025.57 h
246788000	container	08/25, 01:07 AM UTC	-2.63 h	—
246788000	container	08/24, 07:21 PM UTC	-23.08 h	—
248758000	container	08/24, 01:29 AM UTC	-27.33 h	-1494.49 h
244830183	product	08/23, 03:41 AM UTC	-706.05 h	-702.70 h

See it on a live desk

Predicted ETAs, congestion and sanctions screening across 51 ports — try it in one click, no signup.

Open dashboard See pricing →

How it's measured

Predicted ETA: distance-to-berth over speed-made-good, refreshed on every AIS position, with a seasonal correction from rolling medians.
Broadcast ETA: the crew-entered ETA in the vessel's AIS message — the de-facto industry default.
Both are compared to the actual arrival timestamp on the same closed voyages. We report RMSE (penalises large misses) and MAE (typical error).
Broadcast ETAs more than 7 days off are dropped as AIS sentinel / placeholder values, and our model is scored on that same set — so the comparison is honest, not cherry-picked.
Coverage is public AIS only; ports with weak coverage show fewer closed voyages. We'd rather show a small honest sample than a big misleading one.