Mickey Alerts Crowd Lab
The Prediction Scorecard
Anyone can claim their crowd calendar is “AI-powered”. We grade ours in public instead. Every night we compare what we Projected and what our Model said against what was actually Observed — and publish the receipt, including the days we got wrong.
Last 30 days, all parks
Sample: 390,442 model-vs-posted checks · 180 days observed · window Aug 16, 2026 – Sep 14, 2026 · updated Sep 15, 2026.
Trailing 90 days: 49% within ±1 decile (488 park-days), wait MAE 9.2 min across 1,264,479 checks.
Accuracy by park
Projected crowd levels graded against Observed deciles; wait error is our live Model against Disney’s posted times.
| Park | Window | Within ±1 decile | Exact decile | Days scored | Wait MAE | Model checks |
|---|---|---|---|---|---|---|
| Disney California Adventure | 30 days | 30% | 27% | 30 | 13.9 min | 67,507 |
| 90 days | 36% | 28% | 90 | 10.4 min | 239,901 | |
| Disneyland | 30 days | 7% | 7% | 30 | 11.6 min | 119,022 |
| 90 days | 23% | 23% | 90 | 8.2 min | 439,534 | |
| Animal Kingdom | 30 days | 40% | 40% | 30 | 10.8 min | 24,279 |
| 90 days | 42% | 34% | 90 | 9.7 min | 85,583 | |
| EPCOT | 30 days | 63% | 63% | 30 | 12.9 min | 46,694 |
| 90 days | 66% | 40% | 90 | 11.5 min | 166,013 | |
| Hollywood Studios | 30 days | 60% | 33% | 30 | 15.3 min | 31,767 |
| 90 days | 78% | 23% | 64 | 13.5 min | 78,807 | |
| Magic Kingdom | 30 days | 50% | 47% | 30 | 7.8 min | 101,173 |
| 90 days | 64% | 53% | 64 | 6.8 min | 254,641 |
The day-by-day receipt
Each cell is one park-day: projected → observed crowd decile. Green = exact, amber = ±1, red = further off. “·” means that side doesn’t exist for the day (no projection possible, or the day wasn’t observed) — those days are excluded from the rates, never counted as hits.
Disney California Adventure
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Sep 1 | 1/10 (Very light) | 1/10 (Very light) | 0 | 18.2 min | 2,960 |
| Sep 2 | 7/10 (Busy) | 5/10 (Moderate) | 2 | 11.5 min | 2,740 |
| Sep 3 | 1/10 (Very light) | 1/10 (Very light) | 0 | 16.1 min | 3,091 |
| Sep 4 | 1/10 (Very light) | 7/10 (Busy) | 6 | 9.6 min | 2,875 |
| Sep 5 | 4/10 (Light) | 10/10 (Packed) | 6 | 9.9 min | 2,831 |
| Sep 6 | 4/10 (Light) | 1/10 (Very light) | 3 | 12.5 min | 1,912 |
| Sep 7 | 4/10 (Light) | 7/10 (Busy) | 3 | 10.1 min | 1,852 |
| Sep 8 | 1/10 (Very light) | 1/10 (Very light) | 0 | 14.5 min | 1,950 |
| Sep 9 | 7/10 (Busy) | 1/10 (Very light) | 6 | 11.9 min | 2,172 |
| Sep 10 | 1/10 (Very light) | 1/10 (Very light) | 0 | 16 min | 879 |
| Sep 11 | 5/10 (Moderate) | 1/10 (Very light) | 4 | 12.5 min | 1,769 |
| Sep 12 | 7/10 (Busy) | 1/10 (Very light) | 6 | 13.4 min | 1,849 |
| Sep 13 | 5/10 (Moderate) | 1/10 (Very light) | 4 | 11.8 min | 1,417 |
| Sep 14 | 5/10 (Moderate) | 1/10 (Very light) | 4 | 13.1 min | 1,215 |
Disneyland
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Sep 1 | 3/10 (Light) | 1/10 (Very light) | 2 | 15.7 min | 4,688 |
| Sep 2 | 3/10 (Light) | 1/10 (Very light) | 2 | 13.7 min | 4,664 |
| Sep 3 | 6/10 (Moderate) | 3/10 (Light) | 3 | 10.8 min | 4,725 |
| Sep 4 | 3/10 (Light) | 3/10 (Light) | 0 | 9.5 min | 5,039 |
| Sep 5 | 3/10 (Light) | 7/10 (Busy) | 4 | 7.7 min | 4,875 |
| Sep 6 | 3/10 (Light) | 9/10 (Packed) | 6 | 9 min | 3,088 |
| Sep 7 | 3/10 (Light) | 1/10 (Very light) | 2 | 14.1 min | 3,201 |
| Sep 8 | 3/10 (Light) | 3/10 (Light) | 0 | 9.5 min | 2,956 |
| Sep 9 | 3/10 (Light) | 1/10 (Very light) | 2 | 11.9 min | 3,771 |
| Sep 10 | 6/10 (Moderate) | 1/10 (Very light) | 5 | 14.1 min | 1,263 |
| Sep 11 | 3/10 (Light) | 1/10 (Very light) | 2 | 12.4 min | 2,945 |
| Sep 12 | 6/10 (Moderate) | 1/10 (Very light) | 5 | 12.4 min | 3,198 |
| Sep 13 | 3/10 (Light) | 1/10 (Very light) | 2 | 10.1 min | 2,341 |
| Sep 14 | 3/10 (Light) | 1/10 (Very light) | 2 | 11.1 min | 2,042 |
Animal Kingdom
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Sep 1 | 3/10 (Light) | 3/10 (Light) | 0 | 12.7 min | 956 |
| Sep 2 | 3/10 (Light) | 3/10 (Light) | 0 | 13.1 min | 902 |
| Sep 3 | 3/10 (Light) | 3/10 (Light) | 0 | 11.6 min | 951 |
| Sep 4 | 6/10 (Moderate) | 6/10 (Moderate) | 0 | 7.3 min | 997 |
| Sep 5 | 6/10 (Moderate) | 9/10 (Packed) | 3 | 10.5 min | 897 |
| Sep 6 | 6/10 (Moderate) | 9/10 (Packed) | 3 | 8 min | 745 |
| Sep 7 | 3/10 (Light) | 9/10 (Packed) | 6 | 10.9 min | 709 |
| Sep 8 | 3/10 (Light) | 6/10 (Moderate) | 3 | 11 min | 654 |
| Sep 9 | 3/10 (Light) | 6/10 (Moderate) | 3 | 12 min | 832 |
| Sep 10 | 3/10 (Light) | 6/10 (Moderate) | 3 | 8.9 min | 478 |
| Sep 11 | 6/10 (Moderate) | 9/10 (Packed) | 3 | 10.3 min | 658 |
| Sep 12 | 6/10 (Moderate) | 9/10 (Packed) | 3 | 10.5 min | 856 |
| Sep 13 | 6/10 (Moderate) | 9/10 (Packed) | 3 | 12.4 min | 611 |
| Sep 14 | 6/10 (Moderate) | 8/10 (Busy) | 2 | 16.3 min | 634 |
EPCOT
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Sep 1 | 9/10 (Packed) | 9/10 (Packed) | 0 | 13.5 min | 1,928 |
| Sep 2 | 9/10 (Packed) | 9/10 (Packed) | 0 | 13.8 min | 1,915 |
| Sep 3 | 9/10 (Packed) | 9/10 (Packed) | 0 | 14.1 min | 1,895 |
| Sep 4 | 4/10 (Light) | 9/10 (Packed) | 5 | 11.5 min | 1,996 |
| Sep 5 | 4/10 (Light) | 10/10 (Packed) | 6 | 11.6 min | 1,943 |
| Sep 6 | 4/10 (Light) | 10/10 (Packed) | 6 | 11.3 min | 1,359 |
| Sep 7 | 9/10 (Packed) | 9/10 (Packed) | 0 | 14.7 min | 1,440 |
| Sep 8 | 9/10 (Packed) | 9/10 (Packed) | 0 | 11.8 min | 1,116 |
| Sep 9 | 9/10 (Packed) | 9/10 (Packed) | 0 | 13.3 min | 1,612 |
| Sep 10 | 9/10 (Packed) | 9/10 (Packed) | 0 | 14.1 min | 719 |
| Sep 11 | 4/10 (Light) | 9/10 (Packed) | 5 | 12.3 min | 1,340 |
| Sep 12 | 9/10 (Packed) | 9/10 (Packed) | 0 | 11.7 min | 1,333 |
| Sep 13 | 9/10 (Packed) | 9/10 (Packed) | 0 | 12.5 min | 1,134 |
| Sep 14 | 9/10 (Packed) | 9/10 (Packed) | 0 | 12.7 min | 1,112 |
Hollywood Studios
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Sep 1 | 9/10 (Packed) | 7/10 (Busy) | 2 | 16 min | 1,169 |
| Sep 2 | 7/10 (Busy) | 7/10 (Busy) | 0 | 14.7 min | 1,307 |
| Sep 3 | 9/10 (Packed) | 9/10 (Packed) | 0 | 13.3 min | 1,207 |
| Sep 4 | 9/10 (Packed) | 10/10 (Packed) | 1 | 13.5 min | 1,331 |
| Sep 5 | 9/10 (Packed) | 10/10 (Packed) | 1 | 16.5 min | 1,301 |
| Sep 6 | 7/10 (Busy) | 10/10 (Packed) | 3 | 14.1 min | 856 |
| Sep 7 | 7/10 (Busy) | 9/10 (Packed) | 2 | 21.2 min | 942 |
| Sep 8 | 7/10 (Busy) | 10/10 (Packed) | 3 | 10.7 min | 782 |
| Sep 9 | 7/10 (Busy) | 9/10 (Packed) | 2 | 18.9 min | 964 |
| Sep 10 | 7/10 (Busy) | 9/10 (Packed) | 2 | 20.1 min | 449 |
| Sep 11 | 9/10 (Packed) | 10/10 (Packed) | 1 | 12.4 min | 861 |
| Sep 12 | 9/10 (Packed) | 9/10 (Packed) | 0 | 15.5 min | 1,022 |
| Sep 13 | 8/10 (Busy) | 9/10 (Packed) | 1 | 14.4 min | 859 |
| Sep 14 | 7/10 (Busy) | 9/10 (Packed) | 2 | 17.4 min | 638 |
Magic Kingdom
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Sep 1 | 1/10 (Very light) | 1/10 (Very light) | 0 | 11.4 min | 4,068 |
| Sep 2 | 5/10 (Moderate) | 1/10 (Very light) | 4 | 9 min | 3,693 |
| Sep 3 | 5/10 (Moderate) | 1/10 (Very light) | 4 | 8.5 min | 3,901 |
| Sep 4 | 1/10 (Very light) | 1/10 (Very light) | 0 | 7.3 min | 3,732 |
| Sep 5 | 5/10 (Moderate) | 5/10 (Moderate) | 0 | 6.6 min | 4,258 |
| Sep 6 | 5/10 (Moderate) | 5/10 (Moderate) | 0 | 5.6 min | 2,657 |
| Sep 7 | 5/10 (Moderate) | 1/10 (Very light) | 4 | 8.4 min | 2,731 |
| Sep 8 | 1/10 (Very light) | 1/10 (Very light) | 0 | 9.7 min | 2,627 |
| Sep 9 | 5/10 (Moderate) | 5/10 (Moderate) | 0 | 6.1 min | 3,797 |
| Sep 10 | 5/10 (Moderate) | 5/10 (Moderate) | 0 | 6.3 min | 1,459 |
| Sep 11 | 1/10 (Very light) | 1/10 (Very light) | 0 | 10.1 min | 2,740 |
| Sep 12 | 5/10 (Moderate) | 5/10 (Moderate) | 0 | 6.3 min | 3,183 |
| Sep 13 | 5/10 (Moderate) | 1/10 (Very light) | 4 | 9.1 min | 2,457 |
| Sep 14 | 5/10 (Moderate) | 5/10 (Moderate) | 0 | 6.5 min | 2,196 |
Our biggest misses
Biggest misses are shown, not buried: every crowd projection 2+ deciles off and the worst attraction-day model errors (at least 12 model-vs-posted checks) from the trailing 90 days, worst first.
- Crowd projectionWe projected Busy (7/10) for Disney California Adventure on Sep 12, 2026; the day ran Very light (1/10).
- Wait modelOur wait model averaged 74.1 min off Disney's posted wait at Space Mountain (Magic Kingdom, Aug 6, 2026) — model 42 min vs posted 116 min across 184 checks.
- Crowd projectionWe projected Busy (7/10) for Disney California Adventure on Sep 9, 2026; the day ran Very light (1/10).
- Wait modelOur wait model averaged 70.7 min off Disney's posted wait at Haunted Mansion Holiday (Disneyland, Aug 24, 2026) — model 103 min vs posted 32 min across 98 checks.
- Crowd projectionWe projected Light (3/10) for Animal Kingdom on Sep 7, 2026; the day ran Packed (9/10).
- Wait modelOur wait model averaged 70 min off Disney's posted wait at Star Wars: Rise of the Resistance (Hollywood Studios, Aug 7, 2026) — model 59 min vs posted 128 min across 127 checks.
- Crowd projectionWe projected Light (3/10) for Disneyland on Sep 6, 2026; the day ran Packed (9/10).
- Wait modelOur wait model averaged 65.7 min off Disney's posted wait at Haunted Mansion Holiday (Disneyland, Aug 31, 2026) — model 87 min vs posted 22 min across 155 checks.
- Crowd projectionWe projected Light (4/10) for EPCOT on Sep 6, 2026; the day ran Packed (10/10).
- Wait modelOur wait model averaged 62.4 min off Disney's posted wait at Haunted Mansion Holiday (Disneyland, Aug 30, 2026) — model 85 min vs posted 23 min across 145 checks.
How the grading works
Crowd levels. Crowd projections are graded eve-of-day: for each park-day we replay the decile (1–10) the calendar's seasonal projection implied using only history available before that date, and compare it with the decile the observed park-wide median wait landed at on that same scale. Days without observed stats are excluded from the rates — never counted as hits.
Wait times. Wait error is the live model-vs-posted comparison: every few minutes our standby-wait model predicts each attraction's current wait and is graded against the wait Disney was posting at that same moment. MAE is the pair-weighted mean absolute error in minutes; bias is the signed mean (positive = model runs high).
The same honesty labels apply here as everywhere in the Crowd Lab: Observed means recorded from Disney’s posted waits, Typical means a historical range, Model means a machine-learning estimate shown next to observed data, and Projected means a seasonal projection for a calendar date.
What we don’t publish (yet)
We collect wait times every minute, but we do not publish minute-level predictions for future dates. Our research nowcasts currently beat a persistence baseline at 30-, 60-, and 120-minute horizons, while the 15-minute horizon still loses to simply assuming the current wait holds — so none of them ship as public forecasts. Graduation criteria: a nowcast becomes public only when its 15-minute horizon beats persistence and it passes forward validation. Until then, future dates only ever show seasonal projections and typical ranges, labeled as such.
Use the predictions we do publish
- The crowd calendar scores every park and day 1–10 — the projections this page grades.
- The live wait-times boards show the model’s current predictions next to Disney’s posted waits, so you can judge it in real time.
- The park planner (The Club plan) turns the same models into an optimized day plan.
FAQ
What is the prediction scorecard?
It is a continuously updated receipt for our own predictions. Every night we grade the previous day: the crowd level (1–10) our calendar projected for each park versus the level the observed waits actually produced, and how far our live wait-time model was from the waits Disney posted. Hit rates, error in minutes, and the biggest misses are all published here.
How is the crowd projection graded?
Eve-of-day replay: for each park-day we recompute what our seasonal projection implied using only history available before that date, then compare it with the decile the observed park-wide median wait landed at on that same scale. Days without observed data are excluded from the rates — they are never counted as hits.
How is the wait-time model graded?
Every few minutes our standby-wait model predicts each attraction’s current wait, and each prediction is stored next to the wait Disney was posting at that same moment. The scorecard reports the mean absolute error in minutes, weighted by the number of model-vs-posted checks.
Why don’t you publish minute-level forecasts for future dates?
Because they haven’t earned it yet. Our research nowcasts beat a persistence baseline at 30–120-minute horizons, but the 15-minute horizon still loses to assuming the current wait holds. A nowcast graduates to this site only when its 15-minute horizon beats persistence and passes forward validation. Until then, future dates only show labeled seasonal projections and typical ranges.
All grades are against Mickey Alerts’ own recorded observations of Disney’s posted wait times. Not affiliated with The Walt Disney Company, Disney Parks, or Disney Vacation Club.