What this page shows
How well the forecasting model is doing, per series. Every 5
minutes the service compares the model's predictions to what actually
happened and writes a score. This table shows the latest score for
each active series.
The three numbers
- MAPE — Mean Absolute Percentage Error. "On
average, how far off was the prediction?" Lower is better.
Green ≤ 15 %, amber ≤ 30 %, red worse.
Note: for signals that hover near zero, MAPE can spike for harmless
reasons (dividing by something tiny) — don't panic at one big red row.
- Coverage — "Of the actual readings, how many
fell inside the predicted uncertainty band?" The band is built so
about 80 % should fall in if the model is well calibrated.
Coverage near 80 % is healthy; much lower means the model is too
confident.
- Drift — fraction of recent readings that were
far from the prediction. A sustained high drift score means the
pattern of the signal has changed and the model should be retrained
on fresh data.
What happens automatically
If more than half of all active series are drifting
at the same time, that's almost always an upstream problem (sensor
outage, clock skew). The service logs a drift.widespread
warning but deliberately doesn't auto-retrain — a human should look
first.
Filtering
Use the dropdowns at the top to narrow to a zone, division, station
or single asset — each choice limits the next, and every level is
optional. Once an asset is picked you can also focus on one parameter.
Clear drops all filters.
How to use this page
Sort by drift to find series whose model has gone stale. Sort by
coverage (low → high) to find the series most often producing
suspicious-looking readings.