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
ObservedSample: 421,289 model-vs-posted checks · 180 days observed · window Sep 27, 2026 – Oct 26, 2026 · updated Oct 28, 2026.
Trailing 90 days: 44% within ±1 decile (540 park-days), wait MAE 10 min across 1,175,709 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 | 47% | 7% | 30 | 10.9 min | 73,874 |
| 90 days | 41% | 16% | 90 | 11.5 min | 202,655 | |
| Disneyland | 30 days | 30% | 3% | 30 | 8.3 min | 124,470 |
| 90 days | 39% | 12% | 90 | 9.2 min | 354,955 | |
| Animal Kingdom | 30 days | 40% | 13% | 30 | 11.9 min | 27,020 |
| 90 days | 27% | 10% | 90 | 10.8 min | 74,422 | |
| EPCOT | 30 days | 43% | 0% | 30 | 12.3 min | 50,970 |
| 90 days | 58% | 18% | 90 | 12.2 min | 140,834 | |
| Hollywood Studios | 30 days | 40% | 3% | 30 | 13.9 min | 32,705 |
| 90 days | 53% | 13% | 90 | 14 min | 93,857 | |
| Magic Kingdom | 30 days | 50% | 27% | 30 | 7.4 min | 112,250 |
| 90 days | 48% | 28% | 90 | 7.3 min | 308,986 |
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 |
|---|---|---|---|---|---|
| Oct 13 | 1/10 (Very light) | 6/10 (Moderate) | 5 | 13.3 min | 3,033 |
| Oct 14 | 7/10 (Busy) | 10/10 (Packed) | 3 | 9.7 min | 3,033 |
| Oct 15 | 1/10 (Very light) | 5/10 (Moderate) | 4 | 14.6 min | 2,862 |
| Oct 16 | 7/10 (Busy) | 10/10 (Packed) | 3 | 8.4 min | 2,707 |
| Oct 17 | 9/10 (Packed) | 10/10 (Packed) | 1 | 9.7 min | 2,868 |
| Oct 18 | 3/10 (Light) | 2/10 (Very light) | 1 | 15.3 min | 3,162 |
| Oct 19 | 7/10 (Busy) | 9/10 (Packed) | 2 | 7.3 min | 2,989 |
| Oct 20 | 1/10 (Very light) | 2/10 (Very light) | 1 | 14 min | 3,155 |
| Oct 21 | 7/10 (Busy) | 4/10 (Light) | 3 | 7.9 min | 2,817 |
| Oct 22 | 1/10 (Very light) | 2/10 (Very light) | 1 | 9.8 min | 2,976 |
| Oct 23 | 7/10 (Busy) | 8/10 (Busy) | 1 | 7.8 min | 2,731 |
| Oct 24 | 8/10 (Busy) | 9/10 (Packed) | 1 | 8.8 min | 2,981 |
| Oct 25 | 5/10 (Moderate) | 3/10 (Light) | 2 | 13.1 min | 3,158 |
| Oct 26 | 7/10 (Busy) | 8/10 (Busy) | 1 | 8.3 min | 2,875 |
Disneyland
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Oct 13 | 7/10 (Busy) | 9/10 (Packed) | 2 | 6.8 min | 4,830 |
| Oct 14 | 6/10 (Moderate) | 5/10 (Moderate) | 1 | 9.3 min | 5,208 |
| Oct 15 | 9/10 (Packed) | 8/10 (Busy) | 1 | 6.8 min | 5,062 |
| Oct 16 | 7/10 (Busy) | 9/10 (Packed) | 2 | 6.4 min | 5,326 |
| Oct 17 | 9/10 (Packed) | 8/10 (Busy) | 1 | 6.5 min | 5,168 |
| Oct 18 | 6/10 (Moderate) | 3/10 (Light) | 3 | 8.4 min | 4,835 |
| Oct 19 | 6/10 (Moderate) | 6/10 (Moderate) | 0 | 6.3 min | 4,994 |
| Oct 20 | 6/10 (Moderate) | 3/10 (Light) | 3 | 9.2 min | 4,973 |
| Oct 21 | 3/10 (Light) | 1/10 (Very light) | 2 | 10.7 min | 4,736 |
| Oct 22 | 9/10 (Packed) | 2/10 (Very light) | 7 | 9.1 min | 4,978 |
| Oct 23 | 7/10 (Busy) | 9/10 (Packed) | 2 | 6.6 min | 4,752 |
| Oct 24 | 7/10 (Busy) | 6/10 (Moderate) | 1 | 6.6 min | 5,440 |
| Oct 25 | 6/10 (Moderate) | 4/10 (Light) | 2 | 8.6 min | 5,123 |
| Oct 26 | 7/10 (Busy) | 6/10 (Moderate) | 1 | 7.6 min | 4,857 |
Animal Kingdom
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Oct 13 | 6/10 (Moderate) | 9/10 (Packed) | 3 | 16.4 min | 1,089 |
| Oct 14 | 6/10 (Moderate) | 8/10 (Busy) | 2 | 15.3 min | 1,092 |
| Oct 15 | 3/10 (Light) | 9/10 (Packed) | 6 | 10.4 min | 1,044 |
| Oct 16 | 6/10 (Moderate) | 9/10 (Packed) | 3 | 13.6 min | 894 |
| Oct 17 | 6/10 (Moderate) | 9/10 (Packed) | 3 | 14.4 min | 1,184 |
| Oct 18 | 6/10 (Moderate) | 8/10 (Busy) | 2 | 10.8 min | 1,119 |
| Oct 19 | 6/10 (Moderate) | 7/10 (Busy) | 1 | 11.1 min | 1,089 |
| Oct 20 | 6/10 (Moderate) | 8/10 (Busy) | 2 | 8 min | 1,172 |
| Oct 21 | 6/10 (Moderate) | 6/10 (Moderate) | 0 | 10.1 min | 1,089 |
| Oct 22 | 6/10 (Moderate) | 6/10 (Moderate) | 0 | 8.3 min | 1,074 |
| Oct 23 | 8/10 (Busy) | 8/10 (Busy) | 0 | 7.3 min | 1,099 |
| Oct 24 | 6/10 (Moderate) | 9/10 (Packed) | 3 | 7.9 min | 1,191 |
| Oct 25 | 6/10 (Moderate) | 7/10 (Busy) | 1 | 15.1 min | 1,079 |
| Oct 26 | 6/10 (Moderate) | 8/10 (Busy) | 2 | 9.7 min | 1,135 |
EPCOT
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Oct 13 | 8/10 (Busy) | 10/10 (Packed) | 2 | 9.7 min | 2,013 |
| Oct 14 | 8/10 (Busy) | 10/10 (Packed) | 2 | 11.9 min | 2,037 |
| Oct 15 | 8/10 (Busy) | 10/10 (Packed) | 2 | 12.5 min | 2,404 |
| Oct 16 | 8/10 (Busy) | 10/10 (Packed) | 2 | 12.3 min | 2,036 |
| Oct 17 | 8/10 (Busy) | 10/10 (Packed) | 2 | 11.3 min | 2,001 |
| Oct 18 | 8/10 (Busy) | 9/10 (Packed) | 1 | 11.7 min | 2,076 |
| Oct 19 | 8/10 (Busy) | 9/10 (Packed) | 1 | 14.1 min | 2,146 |
| Oct 20 | 8/10 (Busy) | 9/10 (Packed) | 1 | 10.7 min | 1,968 |
| Oct 21 | 8/10 (Busy) | 9/10 (Packed) | 1 | 12.9 min | 2,017 |
| Oct 22 | 8/10 (Busy) | 9/10 (Packed) | 1 | 12.4 min | 1,832 |
| Oct 23 | 8/10 (Busy) | 10/10 (Packed) | 2 | 10.8 min | 1,871 |
| Oct 24 | 8/10 (Busy) | 10/10 (Packed) | 2 | 11.8 min | 2,046 |
| Oct 25 | 8/10 (Busy) | 9/10 (Packed) | 1 | 13.6 min | 2,053 |
| Oct 26 | 8/10 (Busy) | 9/10 (Packed) | 1 | 13.5 min | 2,095 |
Hollywood Studios
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Oct 13 | 8/10 (Busy) | 10/10 (Packed) | 2 | 11.6 min | 1,309 |
| Oct 14 | 7/10 (Busy) | 10/10 (Packed) | 3 | 11.6 min | 1,406 |
| Oct 15 | 8/10 (Busy) | 10/10 (Packed) | 2 | 9.6 min | 1,220 |
| Oct 16 | 9/10 (Packed) | 10/10 (Packed) | 1 | 11.6 min | 1,327 |
| Oct 17 | 8/10 (Busy) | 10/10 (Packed) | 2 | 13.7 min | 1,311 |
| Oct 18 | 8/10 (Busy) | 9/10 (Packed) | 1 | 13.6 min | 1,293 |
| Oct 19 | 8/10 (Busy) | 9/10 (Packed) | 1 | 14.1 min | 1,281 |
| Oct 20 | 8/10 (Busy) | 8/10 (Busy) | 0 | 19.8 min | 1,298 |
| Oct 21 | 7/10 (Busy) | 10/10 (Packed) | 3 | 10.8 min | 1,319 |
| Oct 22 | 8/10 (Busy) | 9/10 (Packed) | 1 | 15.7 min | 1,269 |
| Oct 23 | 8/10 (Busy) | 10/10 (Packed) | 2 | 11.3 min | 1,331 |
| Oct 24 | 8/10 (Busy) | 10/10 (Packed) | 2 | 9.9 min | 1,324 |
| Oct 25 | 8/10 (Busy) | 9/10 (Packed) | 1 | 16.2 min | 1,245 |
| Oct 26 | 8/10 (Busy) | 9/10 (Packed) | 1 | 14.3 min | 1,297 |
Magic Kingdom
View this receipt as a table
| Date | Projected | Observed | Deciles off | Wait MAE | Model checks |
|---|---|---|---|---|---|
| Oct 13 | 5/10 (Moderate) | 4/10 (Light) | 1 | 7 min | 4,547 |
| Oct 14 | 9/10 (Packed) | 10/10 (Packed) | 1 | 10.2 min | 4,676 |
| Oct 15 | 5/10 (Moderate) | 2/10 (Very light) | 3 | 9.6 min | 4,462 |
| Oct 16 | 5/10 (Moderate) | 3/10 (Light) | 2 | 7.1 min | 4,380 |
| Oct 17 | 9/10 (Packed) | 9/10 (Packed) | 0 | 6.3 min | 4,874 |
| Oct 18 | 5/10 (Moderate) | 3/10 (Light) | 2 | 6.5 min | 4,518 |
| Oct 19 | 5/10 (Moderate) | 5/10 (Moderate) | 0 | 7.1 min | 4,178 |
| Oct 20 | 5/10 (Moderate) | 7/10 (Busy) | 2 | 5.8 min | 4,151 |
| Oct 21 | 9/10 (Packed) | 3/10 (Light) | 6 | 6.4 min | 4,270 |
| Oct 22 | 5/10 (Moderate) | 1/10 (Very light) | 4 | 9.7 min | 4,328 |
| Oct 23 | 5/10 (Moderate) | 2/10 (Very light) | 3 | 7 min | 4,558 |
| Oct 24 | 9/10 (Packed) | 8/10 (Busy) | 1 | 6.6 min | 4,739 |
| Oct 25 | 5/10 (Moderate) | 1/10 (Very light) | 4 | 8.9 min | 4,565 |
| Oct 26 | 5/10 (Moderate) | 6/10 (Moderate) | 1 | 5.8 min | 4,166 |
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 Packed (9/10) for Disneyland on Oct 22, 2026; the day ran Very light (2/10).
- Wait modelOur wait model averaged 83.7 min off Disney's posted wait at 412862995 (Animal Kingdom, Oct 11, 2026) — model 105 min vs posted 21 min across 68 checks.
- Crowd projectionWe projected Light (3/10) for Disneyland on Sep 21, 2026; the day ran Packed (10/10).
- 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 Light (3/10) for Disneyland on Sep 6, 2026; the day ran Packed (10/10).
- 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 Packed (9/10) for Magic Kingdom on Oct 21, 2026; the day ran Light (3/10).
- 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 Animal Kingdom on Oct 15, 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.
We grade the models. The park planner puts them to work.
The park planner, free to use without signing in, runs the same crowd projections and wait models over your own date, must-rides and meals — and reoptimizes the day as the park moves.
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. Scoring revision 2026-10-tie-aware (since 2026-10-06): each day is ranked by its park-wide median standby wait, then its average wait, and tied days share one mid-rank level.
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 (free to use without signing in) 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. Scoring revision 2026-10-tie-aware (October 2026): each day is ranked by its park-wide median standby wait, then its average wait, against every day that park has on record, and tied days share one mid-rank level — so a repeated wait value never pins a whole stretch of days to a 1.
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.