ETA accuracy benchmark · 🇫🇷 Saint-Nazaire / Montoir
How Port Flow's predicted ETA compares to each vessel's own broadcast ETA at Saint-Nazaire / Montoir, 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)
223.24 h
MAE 64.14 h · 30 voyages
Broadcast ETA (RMSE)
Building…
only 18 comparable voyages so far (need 20)
Gap
—
benchmark builds as more voyages close
Closed voyages
error = predicted/broadcast minus actual arrival (hours)| 228020700 | container | 08/26, 03:59 PM UTC | 0.68 h | 5.50 h |
| 636025212 | general-cargo | 08/26, 11:02 AM UTC | 0.07 h | -1177.04 h |
| 228025700 | container | 08/26, 07:37 AM UTC | 0.46 h | -1.37 h |
| 304473000 | container | 08/26, 03:53 AM UTC | 0.14 h | -1.89 h |
| 250001723 | container | 08/26, 02:50 AM UTC | 2.44 h | -20.85 h |
| 255954000 | product | 08/26, 01:51 AM UTC | 0.53 h | 27.15 h |
| 244909000 | container | 08/26, 12:46 AM UTC | -0.13 h | — |
| 249435000 | product | 08/25, 10:07 PM UTC | 2.11 h | -314.12 h |
| 244909000 | container | 08/25, 08:12 PM UTC | -0.29 h | — |
| 224876000 | container | 08/25, 07:56 PM UTC | 0.08 h | -128.94 h |
| 244909000 | container | 08/25, 05:29 PM UTC | -0.39 h | — |
| 228024800 | container | 08/25, 03:55 PM UTC | 1.46 h | 3080.08 h |
| 636021944 | product | 08/25, 02:10 PM UTC | -0.96 h | -144.18 h |
| 244909000 | container | 08/25, 12:05 PM UTC | 0.04 h | — |
| 538006120 | product | 08/25, 03:22 AM UTC | 3.25 h | -47.17 h |
| 229767000 | product | 08/25, 01:18 AM UTC | -0.15 h | -3.31 h |
| 255954000 | chemical | 08/24, 03:13 PM UTC | 0.50 h | -2.72 h |
| 256579000 | general-cargo | 08/24, 11:04 AM UTC | 0.58 h | -0.07 h |
| 304509000 | container | 08/24, 08:24 AM UTC | 0.76 h | -3.92 h |
| 266002000 | product | 08/24, 08:24 AM UTC | 1.97 h | -464.39 h |
| 228024800 | container | 08/23, 03:37 PM UTC | 0.47 h | -144.88 h |
| 538005645 | product | 08/23, 01:36 PM UTC | 0.51 h | -11.60 h |
| 255916071 | container | 08/23, 11:37 AM UTC | 2.04 h | -112.62 h |
| 226340000 | product | 08/23, 01:37 AM UTC | 1.08 h | -183.62 h |
| 218627000 | general-cargo | 08/22, 07:05 PM UTC | -0.17 h | -458.58 h |
| 636026247 | container | 08/22, 05:24 PM UTC | 0.60 h | -77.41 h |
| 215994000 | product | 08/22, 02:42 PM UTC | -94.43 h | -116.70 h |
| 227681520 | product | 08/22, 02:40 PM UTC | -104.78 h | -100.17 h |
| 229632000 | product | 08/22, 02:40 PM UTC | -963.48 h | -919.67 h |
| 228020700 | container | 08/22, 02:37 PM UTC | -739.54 h | -390.62 h |
See it on a live desk
Predicted ETAs, congestion and sanctions screening across 51 ports — try it in one click, no signup.
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.