Erzurum BB v Kasimpasa — Prediction, Odds & Stats
Sunday 13 December 2026 · TUR-Super Lig · 2627
TUR-Super Lig
results-only Prediction generated
AI prediction
ai-blend v1.0 dailyRaw model output; no calibration record for this fixture's bands yet.
Top 5 scorelines
- 1-1 13.6%
- 0-1 11.2%
- 0-0 9.6%
- 0-2 9.5%
- 1-2 9.3%
Goals
| Over 2.5 | 45.3% | Under 2.5 | 54.7% |
| BTTS yes | 49.9% | BTTS no | 50.1% |
| Erzurum BB 1+ | 62.4% | Erzurum BB 2+ | 25.7% |
| Kasimpasa 1+ | 77.9% | Kasimpasa 2+ | 44.5% |
Expected goals 0.98 – 1.51. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Kasimpasa carry the stronger rating, 1487 Elo against 1458.
Risk factors
- Data quality is 45/100, so this price rests on less than the model would like.
- Erzurum BB have only 4 matches on record.
Why the model thinks this
The price
Kasimpasa have an estimated 48.2% win probability, against 28.6% for the draw and 23.2% for Erzurum BB. Expected goals from the ensemble are 0.98 for Erzurum BB and 1.51 for Kasimpasa.
Why Erzurum BB
Nothing in the data singles out Erzurum BB.
Why the draw is live
The draw sits at 28.6%. Draws run at 26% in this competition.
Why Kasimpasa can win
Kasimpasa carry the stronger rating, 1487 Elo against 1458.
Key players
No player-level data for this fixture; the leagues with lineups are the big five.
Availability
No lineup on record for Erzurum BB, so availability is unknown. No lineup on record for Kasimpasa, so availability is unknown.
The matchup, as far as the data reaches
Erzurum BB: 45% possession, 8.5 shots a match, 15.0 faced, 0.30 xG a match from set pieces. Kasimpasa: 34% possession, 8.4 shots a match, 13.4 faced, 0.30 xG a match from set pieces.
Inputs last refreshed: matches 2026-10-24 13:59 · team_stats 2026-10-24 06:04 · availability 2026-10-24 14:57 · prediction 2026-09-18 10:37 ·
Kasimpasa are the model's most likely outcome at 48.2%. The likeliest scoreline is 1-1 at 13.6%. Confidence 61/100, data quality 45/100. 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 | 0.98–1.51 | 0% | 0% | 0% | |
| dc-xg | 0.75–1.61 | 0-1 14% | 42% | 43% |
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.