Model lowers Phoenix departure delay risk 3–6 PM Friday to 68%
- Current state
- Resolved: closed without a new report (The forecast window has started; measured delays are reported separately as observed items.)
- Started
- Latest activity
- Updates
- 4
Tailodds reports what the FAA publishes, what we measure and what our model forecasts. It doesn’t control airport operations or change bookings; check with your airline about your trip.
Updates oldest first
-
Initial Forecast
Model forecasts 55% delay risk for Phoenix departures 3–6 PM Friday
Tailodds’ model gives the 117 departures scheduled from Phoenix 3–6 PM Friday an average 55% chance of leaving 15+ minutes late. With calm weather the same flights would average 36%. From the 4:00 PM MST forecast (model famA-fc-v3). This is a forecast, not a report of delays.
Evidence for this update
Target PHX departures 3–6 PM 2026-10-30 (15+ min late) Probability (calibrated, mean per flight) 55% over 117 flights Forecast cycle · horizon Thu Oct 29, 4:00 PM MST · 22.0 h ahead Model version famA-fc-v3 Source event time Ingested Published here (2026-10-29 23:58 UTC) Sources Tailodds forecast Provenance forecast_blocks forecast-blocks-v1 · config 2026-10-17.1 · writer template-v1 Was this useful? -
Escalation Forecast
Updated model puts Phoenix departure delay risk 3–6 PM Friday at 63%
What changed: 55% → 63% since the 4:00 PM MST forecast (model changed)
Tailodds’ model gives the 120 departures scheduled from Phoenix 3–6 PM Friday an average 63% chance of leaving 15+ minutes late. With calm weather the same flights would average 38%. From the 6:00 AM MST forecast (model famB-sd-v4i). The model changed since the previous item (from famA-fc-v3), so some or all of this change comes from the new model rather than new information. This is a forecast, not a report of delays.
Evidence for this update
Target PHX departures 3–6 PM 2026-10-30 (15+ min late) Probability (calibrated, mean per flight) 63% over 120 flights Forecast cycle · horizon Fri Oct 30, 6:00 AM MST · 7.5 h ahead Model version famB-sd-v4i (changed since the previous update) Source event time Ingested Published here (2026-10-30 14:27 UTC) Sources Tailodds forecast Provenance forecast_blocks forecast-blocks-v1 · config 2026-10-17.1 · writer template-v1 Was this useful? -
Escalation Forecast
Model raises Phoenix departure delay risk 3–6 PM Friday to 79%
What changed: 63% → 79% since the 6:00 AM MST forecast (same model, same window)
Tailodds’ model gives the 120 departures scheduled from Phoenix 3–6 PM Friday an average 79% chance of leaving 15+ minutes late. With calm weather the same flights would average 43%. From the 9:00 AM MST forecast (model famB-sd-v4i). This is a forecast, not a report of delays.
Evidence for this update
Target PHX departures 3–6 PM 2026-10-30 (15+ min late) Probability (calibrated, mean per flight) 79% over 120 flights Forecast cycle · horizon Fri Oct 30, 9:00 AM MST · 5.1 h ahead Model version famB-sd-v4i Source event time Ingested Published here (2026-10-30 16:56 UTC) Sources Tailodds forecast Provenance forecast_blocks forecast-blocks-v1 · config 2026-10-17.1 · writer template-v1 Was this useful? -
De-escalation Forecast
Model lowers Phoenix departure delay risk 3–6 PM Friday to 68%
What changed: 79% → 68% since the 9:00 AM MST forecast (same model, same window)
Tailodds’ model gives the 122 departures scheduled from Phoenix 3–6 PM Friday an average 68% chance of leaving 15+ minutes late. With calm weather the same flights would average 43%. From the 2:00 PM MST forecast (model famB-sd-v4i). This is a forecast, not a report of delays.
Evidence for this update
Target PHX departures 3–6 PM 2026-10-30 (15+ min late) Probability (calibrated, mean per flight) 68% over 122 flights Forecast cycle · horizon Fri Oct 30, 2:00 PM MST · 0.1 h ahead Model version famB-sd-v4i Source event time Ingested Published here (2026-10-30 21:56 UTC) Sources Tailodds forecast Provenance forecast_blocks forecast-blocks-v1 · config 2026-10-17.1 · writer template-v1 Was this useful?
Closed Fri Oct 30, 3:01 PM MST: The forecast window has started; measured delays are reported separately as observed items.