Sunday, 20/09/2026 at 17:00
Full timeNPS Volos 1:2 AEK Athens
AEK Athens were the model's likeliest winner before kick-off at 57%. They won 2–1. The biggest difference was NPS Volos's attack: 1.53 xG against 0.87 projected (+0.66).
Goals
- 61' Luka Jović (pen.) AEK Athens · 0.82 xG chance 0–1
- 85' Georgios Charalampoglou NPS Volos · 0.19 xG chance 1–1
- 88' Luka Jović AEK Athens · 0.18 xG chance 1–2
The model against the result
- NPS Volos
- 16%
- Draw
- 27%
- AEK Athens
- 57% What happened
Data coverage Both teams have the full 20-match model window available.
Projected vs produced
NPS Volos produced 0.66 xG more than projected
Projected before kick-off Produced on the night
The shots behind it
- Shots
- 12
- 11
- On target
- 4
- 2
- Inside the box
- 8
- 7
- xG per shot
- 0.13
- 0.17
- Open play xG
- 1.22
- 1.03
- Set-piece xG
- 0.35
- 0.04
- Penalties
- 0
- 1
NPS Volos's shots add up to 1.57 xG and AEK Athens's to 1.89; the published figures are 1.53 and 1.85. Leaving out penalties and own goals, NPS Volos's shots come to 1.57 against a published non-penalty xG of 1.53: more than rounding can explain, so the two figures were not read at the same point of the provider's revisions. The provider computes a match's total xG and its non-penalty xG separately, so the difference between the two is not what a penalty was worth. AEK Athens's penalty is worth 0.82 xG in the shot data.
Shot map
Both teams shown attacking the same goal for comparison.
All shots
23 shots · 3.46 xG
Hover or tap a shot, or step through them with the arrows.
- NPS Volos
- AEK Athens
- Filled = goal
- Dot area = xG (the smallest chances drawn at a minimum size)
Figures read 7 November, 17:09 · final
Recent form
0.90 xG created 1.51 xGA
- L 0.42 created, 1.40 conceded against Aris Thessaloniki
- L 1.34 created, 1.79 conceded against OFI Crete
- L 0.91 created, 1.40 conceded against OFI Crete
- D 1.31 created, 0.56 conceded against Iraklis 1908
- D 0.41 created, 1.62 conceded against Olympiacos FC
- L 1.00 created, 2.27 conceded against PS Kalamata
1.71 xG created 0.92 xGA
- D 1.02 created, 1.35 conceded against PAOK
- D 0.78 created, 0.62 conceded against Olympiacos FC
- W 2.06 created, 0.38 conceded against Iraklis 1908
- D 0.48 created, 1.26 conceded against AE Kifisia
- W 3.53 created, 0.40 conceded against Aris Thessaloniki
- D 2.42 created, 1.52 conceded against Asteras Aktor
xG created xG conceded (xGA) W / D / L: the match result
Head to head
Pre-match model & market record
4 signals flagged1 won3 lost
- Lost
- Lost
- Won
- Lost
View pre-match record Hide pre-match record
| Selection | Price | Model-implied edge | Result |
|---|---|---|---|
| NPS Volos to win | 9.00 | +40.6% | Lost |
| Draw | 4.75 | +28.4% | Lost |
| Both teams to score | 2.05 | +9.3% | Won |
| Under 2.5 goals | 2.08 | +4.3% | Lost |
Pre-match model vs market
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| NPS Volos | 15.6% | 10.5% | +5.1 pp | 6.40 |
| Draw | 27.0% | 20.0% | +7.1 pp | 3.70 |
| AEK Athens | 57.4% | 69.5% | −12.2 pp | 1.74 |
Other markets
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| Both teams to score | 53.3% | 45.3% | +8.0 pp | 1.88 |
| Both teams not to score | 46.7% | 54.7% | −8.0 pp | 2.14 |
| Over 1.5 goals | 77.5% | 76.6% | +0.9 pp | 1.29 |
| Under 1.5 goals | 22.5% | 23.4% | −0.9 pp | 4.45 |
| Over 2.5 goals | 49.7% | 54.6% | −4.9 pp | 2.01 |
| Under 2.5 goals | 50.3% | 45.4% | +4.9 pp | 1.99 |
Prices and probabilities are the ones stored before kick-off; nothing here is recalculated. The model-implied edge is the model's probability times the price, minus one: what a stake of one would return on average if the model is right, not observed return, so a flagged outcome that lost is the ordinary case rather than a contradiction.
Model details
Show Hide
- Fit window
- the last 20 matches, recency weighted (a match 107 days old counts half)
- NPS Volos sample
- 20 matches
- AEK Athens sample
- 20 matches
- Computed
- 1 day before kick-off
- Prices taken
- 1 day before kick-off
Limitations
The model reads expected goals and nothing else. It does not know the lineups, who is injured or suspended, what either side has to play for, the weather, or how congested the schedule around this match is.