Almería v RC Celta Fortuna — Prediction, Odds & Stats
Sunday 20 September 2026 · ESP-La Liga 2 · 2627
La Liga
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 9.8%
- 2-1 9.6%
- 1-0 8.1%
- 2-0 7.6%
- 1-2 6.3%
Goals
| Over 2.5 | 61.9% | Under 2.5 | 38.1% |
| BTTS yes | 61.1% | BTTS no | 38.9% |
| Almería 1+ | 85.5% | Almería 2+ | 57.4% |
| RC Celta Fortuna 1+ | 71.8% | RC Celta Fortuna 2+ | 36.1% |
Expected goals 1.93 – 1.27. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Almería carry the stronger rating, 1537 Elo against 1501.
Risk factors
- Data quality is 55/100, so this price rests on less than the model would like.
- RC Celta Fortuna have only 3 matches on record.
Why the model thinks this
The price
Almería have an estimated 53.1% win probability, against 25.2% for RC Celta Fortuna and 21.7% for the draw. Expected goals from the ensemble are 1.93 for Almería and 1.27 for RC Celta Fortuna.
Why Almería
Almería carry the stronger rating, 1537 Elo against 1501.
Why the draw is live
The draw sits at 21.7%. Draws run at 27% in this competition.
Why RC Celta Fortuna can win
Nothing in the data singles out RC Celta Fortuna.
Key players
No player-level data for this fixture; the leagues with lineups are the big five.
Availability
No lineup on record for Almería, so availability is unknown. No lineup on record for RC Celta Fortuna, so availability is unknown.
The matchup, as far as the data reaches
Almería: 57% possession, 16.0 shots a match, 12.2 faced, 0.30 xG a match from set pieces. RC Celta Fortuna: 42% possession, 9.0 shots a match, 15.3 faced, 0.30 xG a match from set pieces. Almería's shot volume meets a defence that concedes shots freely.
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 ·
Almería are the model's most likely outcome at 53.1%. The likeliest scoreline is 1-1 at 9.8%. Confidence 49/100, data quality 55/100. 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 | 1.93–1.27 | 0% | 0% | 0% | |
| dc-xg | 1.97–1.39 | 2-1 9% | 65% | 64% |
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.