Sunday, 20/09/2026 at 14:00
Full timeHalmstads BK 2:1 AIK
AIK were the model's likeliest winner before kick-off at 40%. Halmstads BK won 2–1. The biggest difference was AIK's attack: 2.36 xG against 2.04 projected (+0.32).
The model against the result
- Halmstads BK
- 36% What happened
- Draw
- 24%
- AIK
- 40%
Data coverage Both teams have the full 20-match model window available.
Projected vs produced
AIK produced 0.32 xG more than projected
Projected before kick-off Produced on the night
The shots behind it
- Shots
- 18
- 16
- On target
- 10
- 3
- Inside the box
- 12
- 10
- xG per shot
- 0.10
- 0.15
Figures read 7 November, 17:36 · final
Recent form
1.38 xG created 2.56 xGA
2.06 xG created 2.75 xGA
xG created xG conceded (xGA) W / D / L: the match result
Head to head
Pre-match model & market record
4 signals flagged4 won0 lost
- Won
- Won
- Won
- Won
View pre-match record Hide pre-match record
| Selection | Price | Model-implied edge | Result |
|---|---|---|---|
| Both teams to score | 1.67 | +32.0% | Won |
| Over 2.5 goals | 1.65 | +29.3% | Won |
| Halmstads BK to win | 3.25 | +18.2% | Won |
| Over 1.5 goals | 1.18 | +10.4% | Won |
Pre-match model vs market
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| Halmstads BK | 36.4% | 29.0% | +7.4 pp | 2.75 |
| Draw | 23.8% | 26.2% | −2.4 pp | 4.21 |
| AIK | 39.9% | 44.9% | −5.0 pp | 2.51 |
Other markets
| Outcome | Model | Market | Disagreement | Model price |
|---|---|---|---|---|
| Both teams to score | 79.2% | 55.7% | +23.4 pp | 1.26 |
| Both teams not to score | 20.8% | 44.3% | −23.4 pp | 4.80 |
| Over 1.5 goals | 93.4% | 79.2% | +14.2 pp | 1.07 |
| Under 1.5 goals | 6.6% | 20.8% | −14.2 pp | 15.08 |
| Over 2.5 goals | 78.3% | 57.1% | +21.2 pp | 1.28 |
| Under 2.5 goals | 21.7% | 42.9% | −21.2 pp | 4.62 |
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)
- Halmstads BK sample
- 20 matches
- AIK 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.