Deportivo La Coruna v Levante — Prediction, Odds & Stats
Sunday 18 October 2026 · ESP-La Liga · 2627
La Liga
xG 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 11.9%
- 0-1 9.1%
- 1-2 8.8%
- 1-0 8.1%
- 2-1 7.8%
Goals
| Over 2.5 | 52.9% | Under 2.5 | 47.1% |
| BTTS yes | 56.5% | BTTS no | 43.5% |
| Deportivo La Coruna 1+ | 73.2% | Deportivo La Coruna 2+ | 37.8% |
| Levante 1+ | 77.2% | Levante 2+ | 43.5% |
Expected goals 1.32 – 1.48. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Levante have created 1.78 xG a match over their last five while Deportivo La Coruna have allowed 1.90.
- Away from home Levante average 1.31 xG a match.
Risk factors
- Deportivo La Coruna have scored 2.00 a match from 1.33 xG over five matches, which usually corrects.
- Deportivo La Coruna have only 4 matches on record.
Why the model thinks this
The price
Levante have an estimated 41.1% win probability, against 33.7% for Deportivo La Coruna and 25.2% for the draw. Expected goals from the ensemble are 1.31 for Deportivo La Coruna and 1.48 for Levante.
Why Deportivo La Coruna
Deportivo La Coruna have created 1.33 xG a match over their last five while Levante have allowed 1.46. Form is good: 2.00 points a match from the last five. At home Deportivo La Coruna average 0.88 xG a match. Their last eleven was closer to full strength: Levante were missing 0.92 expected goal involvements a match against 0.10.
Why the draw is live
The draw sits at 25.2%. The sides are closely matched on expected goals, 1.31 to 1.48. Draws run at 25% in this competition.
Why Levante can win
Levante have created 1.78 xG a match over their last five while Deportivo La Coruna have allowed 1.90. Away from home Levante average 1.31 xG a match.
Key players
Deportivo La Coruna's leading contributors by expected goal involvements a match: Pierre-Emerick Aubameyang (0.60), Luismi Cruz (0.22), Bil Nsongo (0.21). Levante's leading contributors by expected goal involvements a match: Carlos Espí (0.41), Iván Romero (0.39), Roger Brugué (0.27).
Availability
1 of Levante's top three contributors did not start their last match. 27% of Levante's last eleven are new to the club this window.
The matchup, as far as the data reaches
Deportivo La Coruna: 41% possession, 10.8 shots a match, 13.2 faced, 0.11 xG a match from set pieces. Levante: 43% possession, 12.0 shots a match, 15.4 faced, 0.41 xG a match from set pieces.
Inputs last refreshed: matches 2026-09-08 10:52 · team_stats 2026-09-08 06:03 · availability 2026-09-08 11:54 · prediction 2026-09-04 06:09 ·
Levante are the model's most likely outcome at 41.1%. The likeliest scoreline is 1-1 at 11.9%. Confidence 79/100, data quality 70/100. 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
Deportivo La Coruna are finishing above their chances — 2.7 goals more than expected across 4 matches, which usually cools off. They are also conceding fewer than expected — 2.6 goals saved beyond what the chances suggest.
Levante are finishing below their chances — 2.8 goals fewer than expected across 10 matches, despite creating the openings.
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 |
|---|---|---|---|---|---|
| ai-blend | 1.32–1.48 | 0% | 0% | 0% | |
| dc-xg | 1.68–1.67 | 1-1 10% | 65% | 66% |
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.