Skip to main content
Menu

← All endpoints

Queue Forecast API Online

ML ensemble forecast of queue levels: 24-hour and 7-day (168h) horizons with confidence bounds. The same model that powers nakordoni.eu predictions.

GET https://nakordoni.eu/api/v1/data/forecast — quota class: heavy

ParameterDescription
ppidCheckpoint ID, e.g. id_13 (see /api/v1/data/checkpoints)
prediction_steps24 (default) or 168 for 7-day

Response fields — inside the data object of the envelope. [] marks a list, so data.items[].name is the name field of each element. A field is null, absent or an empty list when we hold no value for it — never a placeholder.

FieldDescription
data[]One element per forecast step, nearest first — 24 or 168 of them.
data[].timeUnix timestamp the step forecasts, with hours_from_now.
data[].avg_carsPredicted queue at that hour.
data[].lower_boundConfidence band around avg_cars, with upper_bound; the _50 pair is the narrower 50% band.
data[].type_of_dataProvenance marker of the input reading the step was built from.
data[].sourceWhich model produced the step, with formula and the corrected flag when a calibrator adjusted it.
data[].learned_multPer-checkpoint learned multiplier applied, and weather_mult the weather one.
data[].v4Full breakdown from the v4 ensemble — component scores behind avg_cars.
curl "https://nakordoni.eu/api/v1/data/forecast?ppid=id_13&prediction_steps=24" \
  -H "Authorization: Bearer NKD-DEV-XXXX-XXXX-XXXX"
🔑 Log in as a developer to try this endpoint live in the sandbox — 50 free test calls a day. Log in