Crystal Palace v Everton — Prediction, Odds & Stats
Sunday 6 September 2026 · FIFA:6vq8j5p3av14nr3iuyi4okhjt · 2627
FIFA:6vq8j5p3av14nr3iuyi4okhjt
results-only Prediction generated
AI prediction
ai-blend v1.0 dailyCalibrated: the model's number corrected by how often calls at that confidence have landed, out of sample (372 settled matches in the thinnest band), then normalised. The smaller figure is the raw model output.
Top 5 scorelines
- 1-1 11.1%
- 0-1 10.5%
- 1-2 9.8%
- 0-2 9.2%
- 1-0 6.3%
Goals
| Over 2.5 | 53.6% | Under 2.5 | 46.4% |
| BTTS yes | 54.1% | BTTS no | 45.9% |
| Crystal Palace 1+ | 65.4% | Crystal Palace 2+ | 28.6% |
| Everton 1+ | 82.8% | Everton 2+ | 52.6% |
Expected goals 1.06 – 1.76. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Everton carry the stronger rating, 1591 Elo against 1528.
- Form is good: 2.20 points a match from the last five.
- They have had 8 days' rest to Crystal Palace's 1.
- Their last eleven was closer to full strength: Crystal Palace were missing 1.24 expected goal involvements a match against 0.47.
Risk factors
- No specific risk flags beyond the usual variance of a football match.
Why the model thinks this
The price
Everton have an estimated 54.8% win probability, against 22.6% for the draw and 22.6% for Crystal Palace. Expected goals from the ensemble are 1.06 for Crystal Palace and 1.76 for Everton.
Why Crystal Palace
At home Crystal Palace average 1.82 xG a match.
Why the draw is live
The draw sits at 22.6%.
Why Everton can win
Everton carry the stronger rating, 1591 Elo against 1528. Form is good: 2.20 points a match from the last five. They have had 8 days' rest to Crystal Palace's 1. Their last eleven was closer to full strength: Crystal Palace were missing 1.24 expected goal involvements a match against 0.47.
Key players
Crystal Palace's leading contributors by expected goal involvements a match: Jean-Philippe Mateta (0.46), Ismaila Sarr (0.44), Yeremi Pino (0.32). Everton's leading contributors by expected goal involvements a match: Kiernan Dewsbury-Hall (0.32), Thierno Barry (0.31), Iliman Ndiaye (0.29).
Availability
2 of Crystal Palace's top three contributors did not start their last match. 27% of Crystal Palace's last eleven are new to the club this window.
The matchup, as far as the data reaches
Crystal Palace: 40% possession, 10.8 shots a match, 18.0 faced, 0.18 xG a match from set pieces. Everton: 48% possession, 15.0 shots a match, 13.4 faced, 0.34 xG a match from set pieces.
Inputs last refreshed: matches 2026-09-06 07:42 · team_stats 2026-09-06 06:08 · availability 2026-09-06 07:53 · prediction 2026-09-05 18:39 ·
Everton are the model's most likely outcome at 54.8%. The likeliest scoreline is 1-1 at 11.1%. Confidence 33/100, data quality 60/100. These are probabilities, not certainties: the less likely outcome happens as often as its number says.
Written from the numbers the model saw, not by a language model; nothing here is a statistic the snapshot does not hold. How predictions work.
Was this pick made in advance?
-oos is out of sample: it was fitted only on matches
played before this one, so its pick is a genuine forecast rather than hindsight.
Anything without that suffix was fitted on all available data.What the chances say
Crystal Palace are finishing sharply below their chances — 5.7 goals fewer than expected across 10 matches, despite creating the openings. They are also conceding more than the chances against them merit — 2.2 goals above expected, which tends to correct.
Everton have scored 15 from 13.7 expected and conceded 18 from 18.2 — both ends in line with the chances, so the recent record is a fair reflection.
Finishing swings far more than chance creation, so a gap this size usually narrows. Over ten matches it is suggestive, not settled — a genuinely elite finisher beats expected goals for years.
What the model said
| Model | Home / Draw / Away | Expected goals | Likeliest score | O2.5 | BTTS |
|---|---|---|---|---|---|
| ai-blend | 1.06–1.76 | 0% | 0% | 0% |
A model whose name ends -oos was produced by the walk-forward backtest:
it was fitted only on matches played before this one, so the pick is genuinely out of sample.