Model raises SFO departure delay risk noon–3 PM Tuesday to 61%
- 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 51% delay risk for SFO departures noon–3 PM Tuesday
Tailodds’ model gives the 113 departures scheduled from SFO noon–3 PM Tuesday an average 51% chance of leaving 15+ minutes late. With calm weather the same flights would average 24%. From the 1:00 PM PST forecast (model famA-fc-v3). This is a forecast, not a report of delays.
Evidence for this update
Target SFO departures noon–3 PM 2026-11-03 (15+ min late) Probability (calibrated, mean per flight) 51% over 113 flights Forecast cycle · horizon Mon Nov 2, 1:00 PM PST · 22.0 h ahead Model version famA-fc-v3 Source event time Ingested Published here (2026-11-02 21:59 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 SFO departure delay risk noon–3 PM Tuesday at 56%
What changed: 51% → 56% since the 1:00 PM PST forecast (model changed)
Tailodds’ model gives the 127 departures scheduled from SFO noon–3 PM Tuesday an average 56% chance of leaving 15+ minutes late. With calm weather the same flights would average 25%. From the 11:00 PM PST forecast (model famA-fc-v3+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 SFO departures noon–3 PM 2026-11-03 (15+ min late) Probability (calibrated, mean per flight) 56% over 127 flights Forecast cycle · horizon Mon Nov 2, 11:00 PM PST · 11.5 h ahead Model version famA-fc-v3+famB-sd-v4i (changed since the previous update) Source event time Ingested Published here (2026-11-03 08:27 UTC) Sources Tailodds forecast Provenance forecast_blocks forecast-blocks-v1 · config 2026-10-17.1 · writer template-v1 Was this useful? -
De-escalation Forecast
Updated model puts SFO departure delay risk noon–3 PM Tuesday at 49%
What changed: 56% → 49% since the 11:00 PM PST forecast (model changed)
Tailodds’ model gives the 127 departures scheduled from SFO noon–3 PM Tuesday an average 49% chance of leaving 15+ minutes late. With calm weather the same flights would average 25%. From the 3:00 AM PST forecast (model famB-sd-v4i). The model changed since the previous item (from famA-fc-v3+famB-sd-v4i), 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 SFO departures noon–3 PM 2026-11-03 (15+ min late) Probability (calibrated, mean per flight) 49% over 127 flights Forecast cycle · horizon Tue Nov 3, 3:00 AM PST · 8.0 h ahead Model version famB-sd-v4i (changed since the previous update) Source event time Ingested Published here (2026-11-03 11:58 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 SFO departure delay risk noon–3 PM Tuesday to 61%
What changed: 49% → 61% since the 3:00 AM PST forecast (same model, same window)
Tailodds’ model gives the 124 departures scheduled from SFO noon–3 PM Tuesday an average 61% chance of leaving 15+ minutes late. With calm weather the same flights would average 47%. From the 10:00 AM PST forecast (model famB-sd-v4i). This is a forecast, not a report of delays.
Evidence for this update
Target SFO departures noon–3 PM 2026-11-03 (15+ min late) Probability (calibrated, mean per flight) 61% over 124 flights Forecast cycle · horizon Tue Nov 3, 10:00 AM PST · 1.0 h ahead Model version famB-sd-v4i Source event time Ingested Published here (2026-11-03 18:58 UTC) Sources Tailodds forecast Provenance forecast_blocks forecast-blocks-v1 · config 2026-10-17.1 · writer template-v1 Was this useful?
Closed Tue Nov 3, 12:00 PM PST: The forecast window has started; measured delays are reported separately as observed items.