Arezzo v Sudtirol — Prediction, Odds & Stats
Sunday 20 September 2026 · ITA-Serie B · 2627
AI prediction
ai-blend v1.0 dailyRaw model output; no calibration record for this fixture's bands yet.
Top 5 scorelines
- 1-1 11.9%
- 2-1 9.8%
- 2-0 8.5%
- 1-0 7.8%
- 0-0 6.3%
Goals
| Over 2.5 | 57.9% | Under 2.5 | 42.1% |
| BTTS yes | 59.1% | BTTS no | 40.9% |
| Arezzo 1+ | 84.4% | Arezzo 2+ | 55.4% |
| Sudtirol 1+ | 68.4% | Sudtirol 2+ | 32.0% |
Expected goals 1.86 – 1.15. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Arezzo carry the stronger rating, 1502 Elo against 1414.
Risk factors
- Data quality is 40/100, so this price rests on less than the model would like.
- Arezzo have only 2 matches on record.
Why the model thinks this
The price
Arezzo have an estimated 52.4% win probability, against 25.4% for the draw and 22.1% for Sudtirol. Expected goals from the ensemble are 1.86 for Arezzo and 1.15 for Sudtirol.
Why Arezzo
Arezzo carry the stronger rating, 1502 Elo against 1414.
Why the draw is live
The draw sits at 25.4%. Draws run at 32% in this competition.
Why Sudtirol can win
Nothing in the data singles out Sudtirol.
Key players
No player-level data for this fixture; the leagues with lineups are the big five.
Availability
No lineup on record for Arezzo, so availability is unknown. No lineup on record for Sudtirol, so availability is unknown.
The matchup, as far as the data reaches
Arezzo: 41% possession, 15.5 shots a match, 14.0 faced, 0.30 xG a match from set pieces. Sudtirol: 47% possession, 15.0 shots a match, 12.4 faced, 0.30 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 ·
Arezzo are the model's most likely outcome at 52.4%. The likeliest scoreline is 1-1 at 11.9%. Confidence 38/100, data quality 40/100. 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 model said
| Model | Home / Draw / Away | Expected goals | Likeliest score | O2.5 | BTTS |
|---|---|---|---|---|---|
| ai-blend | 1.86–1.15 | 0% | 0% | 0% | |
| dc-xg | 2.03–1.15 | 1-1 11% | 61% | 61% |
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.