Pisa v Palermo — Prediction, Odds & Stats
Tuesday 27 October 2026 · ITA-Serie B · 2627
AI prediction
ai-blend v1.0 dailyCalibrated: the model's number corrected by how often calls at that confidence have landed, out of sample (5,276 settled matches in the thinnest band), then normalised. The smaller figure is the raw model output.
Top 5 scorelines
- 1-1 14.7%
- 0-0 10.6%
- 1-0 9.3%
- 0-1 8.8%
- 2-1 8.1%
Goals
| Over 2.5 | 43.7% | Under 2.5 | 56.3% |
| BTTS yes | 51.0% | BTTS no | 49.0% |
| Pisa 1+ | 71.1% | Pisa 2+ | 35.2% |
| Palermo 1+ | 69.4% | Palermo 2+ | 33.2% |
Expected goals 1.24 – 1.18. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Nothing in the data singles out Pisa.
Risk factors
- No specific risk flags beyond the usual variance of a football match.
Why the model thinks this
The price
Pisa have an estimated 37.3% win probability, against 31.4% for Palermo and 31.4% for the draw. Expected goals from the ensemble are 1.24 for Pisa and 1.18 for Palermo.
Why Pisa
Nothing in the data singles out Pisa.
Why the draw is live
The draw sits at 31.4%. The sides are closely matched on expected goals, 1.24 to 1.18. Draws run at 32% in this competition.
Why Palermo can win
Palermo carry the stronger rating, 1625 Elo against 1333. Form is good: 1.80 points a match from the last five.
Key players
Pisa's leading contributors by expected goal involvements a match: Stefano Moreo (0.28), Filip Stojilkovic (0.24), Henrik Meister (0.21).
Availability
1 of Pisa's top three contributors did not start their last match. No lineup on record for Palermo, so availability is unknown.
The matchup, as far as the data reaches
Pisa: 40% possession, 10.6 shots a match, 12.2 faced, 0.12 xG a match from set pieces. Palermo: 50% possession, 14.4 shots a match, 14.8 faced, 0.30 xG a match from set pieces.
Inputs last refreshed: matches 2026-09-05 22:20 · team_stats 2026-09-05 09:41 · availability 2026-09-05 21:03 · prediction 2026-09-05 18:39 ·
Pisa are the model's most likely outcome at 37.3%. The likeliest scoreline is 1-1 at 14.7%. Confidence 47/100, data quality 65/100. 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
Pisa are finishing sharply below their chances — 5.2 goals fewer than expected across 10 matches, despite creating the openings. They are also conceding sharply more than the chances against them merit — 7.9 goals above expected, which tends to correct.
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 |
|---|---|---|---|---|---|
| dc-xg | 1.35–1.04 | 1-1 15% | 43% | 50% |
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.