Feronikeli v Drita — Prediction, Odds & Stats
Wednesday 9 September 2026 · KOS-Superleague · 2627
KOS-Superleague
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
- 0-1 16.0%
- 0-2 12.4%
- 1-1 11.0%
- 0-0 9.5%
- 1-2 9.1%
Goals
| Over 2.5 | 40.9% | Under 2.5 | 59.1% |
| BTTS yes | 40.9% | BTTS no | 59.1% |
| Feronikeli 1+ | 51.9% | Feronikeli 2+ | 16.7% |
| Drita 1+ | 79.5% | Drita 2+ | 47.1% |
Expected goals 0.73 – 1.59. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Away from home Drita average 1.35 xG a match.
Risk factors
- Data quality is 30/100, so this price rests on less than the model would like.
- Feronikeli have only 1 matches on record.
- Drita have only 1 matches on record.
Why the model thinks this
The price
Drita have an estimated 58.2% win probability, against 24.3% for the draw and 17.5% for Feronikeli. Expected goals from the ensemble are 0.73 for Feronikeli and 1.59 for Drita.
Why Feronikeli
At home Feronikeli average 1.35 xG a match.
Why the draw is live
The draw sits at 24.3%. A combined 2.32 expected goals is a low-scoring profile, and low totals mean more level finishes.
Why Drita can win
Away from home Drita average 1.35 xG a match.
Key players
No player-level data for this fixture; the leagues with lineups are the big five.
Availability
No lineup on record for Feronikeli, so availability is unknown. No lineup on record for Drita, so availability is unknown.
The matchup, as far as the data reaches
Feronikeli: 50% possession, 12.0 shots a match, 12.0 faced, 0.30 xG a match from set pieces. Drita: 50% possession, 12.0 shots a match, 12.0 faced, 0.30 xG a match from set pieces.
Inputs last refreshed: matches 2026-09-09 15:30 · team_stats 2026-09-09 06:03 · availability 2026-09-09 15:32 · prediction 2026-09-09 09:54 ·
Drita are the model's most likely outcome at 58.2%. The likeliest scoreline is 0-1 at 16.0%. Confidence 25/100, data quality 30/100. 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 | 0.73–1.59 | 0% | 0% | 0% | |
| dc-xg | 0.49–1.71 | 0-1 19% | 38% | 31% |
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.