Kalamata
21%
Fair odds 4.86
AEK
Model pick
56%
Fair odds 1.79
Share of the pitch
Who wins
| Kalamata | Draw | AEK | |
|---|---|---|---|
| Goals model | 21% | 24% | 56% |
| Elo model | 23% | 27% | 50% |
Why this prediction
-
Overall strength Favours AEK
AEK are rated 158 points above Kalamata (1512 to 1353), built from every result, weighted towards recent ones.
-
Home advantage Favours Kalamata
Playing at home is worth about 65 rating points, which adds 8 points to Kalamata's chance of winning and takes the same from AEK's.
-
Attack against defence Favours AEK
Expected goals 1.1 to 1.9. Kalamata score 0.9 a match against an average side (8th in Greek Super League); AEK concede 1.2 (3rd best defence).
-
Last 5 matches Favours Kalamata
Kalamata DLWWL, gained 12 rating points; AEK LLWLL, lost 23 rating points. Already counted in the ratings above.
Rating, last 12 months
KalamataAEKKalamata
5/9 over 2.5
14 scored
18 conceded
08/22
08/29
09/06
09/13
09/20
10/12
10/18
10/25
11/02
AEK
7/10 over 2.5
21 scored
15 conceded
09/05
09/08
09/13
09/20
10/10
10/14
10/20
10/24
11/01
11/04
Bars show total goals in each of the last 10 matches, oldest on the left: the team's goals in its colour, conceded in grey. The dashed line is 2.5 goals.
Total goals
Both teams to score & clean sheets
Most likely scores
- 1-1
- 1-2
- 0-1
- 0-2
- 1-3
- 0-0
- 0-3
- 2-1
Every score
| 0 | 1 | 2 | 3 | 4 | 5 | |
|---|---|---|---|---|---|---|
| 0 | 6 | 10 | 9 | 6 | 3 | 1 |
| 1 | 5 | 11 | 10 | 6 | 3 | 1 |
| 2 | 3 | 6 | 5 | 3 | 2 | 1 |
| 3 | 1 | 2 | 2 | 1 | 1 | |
| 4 | 1 | |||||
| 5 |
Half-time result
First-half goals
Half-time / full-time
| Half-time ↓ Full-time → | Kalamata | Draw | AEK |
|---|---|---|---|
| Kalamata | 12%8.29 | 5%19.05 | 4%25.97 |
| Level | 8%12.85 | 13%7.41 | 21%4.78 |
| AEK | 1%85.47 | 4%25.77 | 32%3.17 |
Corners
Most corners
Corner totals are hard to call: over 9.5 the model's log loss is 0.685 against 0.693 for a naive guess, across 30,937 past matches. Which side wins more corners is called much better.
Cards
Over 4.5 cards, the model's log loss is 0.653 against 0.682 for a naive guess, across 33,146 past matches. The referee matters a lot and isn't in the model.
They haven't met in the data.