Model raises Philadelphia departure delay risk 9 PM–midnight Thursday to 70%
- 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 40% delay risk for Philadelphia departures 9 PM–midnight Thursday
Tailodds’ model gives the 30 departures scheduled from Philadelphia 9 PM–midnight Thursday an average 40% chance of leaving 15+ minutes late. With calm weather the same flights would average 20%. From the 12:00 PM EST forecast (model famB-sd-v4i). This is a forecast, not a report of delays.
Evidence for this update
Target PHL departures 9 PM–midnight 2026-11-12 (15+ min late) Probability (calibrated, mean per flight) 40% over 30 flights Forecast cycle · horizon Thu Nov 12, 12:00 PM EST · 8.1 h ahead Model version famB-sd-v4i Source event time Ingested Published here (2026-11-12 17:56 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 Philadelphia departure delay risk 9 PM–midnight Thursday to 52%
What changed: 40% → 52% since the 12:00 PM EST forecast (same model, same window)
Tailodds’ model gives the 30 departures scheduled from Philadelphia 9 PM–midnight Thursday an average 52% chance of leaving 15+ minutes late. With calm weather the same flights would average 20%. From the 3:00 PM EST forecast (model famB-sd-v4i). This is a forecast, not a report of delays.
Evidence for this update
Target PHL departures 9 PM–midnight 2026-11-12 (15+ min late) Probability (calibrated, mean per flight) 52% over 30 flights Forecast cycle · horizon Thu Nov 12, 3:00 PM EST · 5.1 h ahead Model version famB-sd-v4i Source event time Ingested Published here (2026-11-12 20:56 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 Philadelphia departure delay risk 9 PM–midnight Thursday to 57%
What changed: 52% → 57% since the 3:00 PM EST forecast (same model, same window)
Tailodds’ model gives the 30 departures scheduled from Philadelphia 9 PM–midnight Thursday an average 57% chance of leaving 15+ minutes late. With calm weather the same flights would average 30%. From the 4:00 PM EST forecast (model famB-sd-v4i). This is a forecast, not a report of delays.
Evidence for this update
Target PHL departures 9 PM–midnight 2026-11-12 (15+ min late) Probability (calibrated, mean per flight) 57% over 30 flights Forecast cycle · horizon Thu Nov 12, 4:00 PM EST · 4.1 h ahead Model version famB-sd-v4i Source event time Ingested Published here (2026-11-12 21:56 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 Philadelphia departure delay risk 9 PM–midnight Thursday to 70%
What changed: 57% → 70% since the 4:00 PM EST forecast (same model, same window)
Tailodds’ model gives the 31 departures scheduled from Philadelphia 9 PM–midnight Thursday an average 70% chance of leaving 15+ minutes late. With calm weather the same flights would average 32%. From the 7:00 PM EST forecast (model famB-sd-v4i). This is a forecast, not a report of delays.
Evidence for this update
Target PHL departures 9 PM–midnight 2026-11-12 (15+ min late) Probability (calibrated, mean per flight) 70% over 31 flights Forecast cycle · horizon Thu Nov 12, 7:00 PM EST · 0.5 h ahead Model version famB-sd-v4i Source event time Ingested Published here (2026-11-13 01:27 UTC) Sources Tailodds forecast Provenance forecast_blocks forecast-blocks-v1 · config 2026-10-17.1 · writer template-v1 Was this useful?
Closed Thu Nov 12, 9:00 PM EST: The forecast window has started; measured delays are reported separately as observed items.