Wednesday, 16/09/2026 at 19:00
Full timeAIK 1:1 Mjällby AIF
AIK were the model's likeliest winner before kick-off at 40%. It finished 1–1. The biggest difference was AIK's attack: 3.15 xG against 1.98 projected (+1.17). Mjällby AIF produced 2.14 xG against 1.87 projected (+0.27).
The model against the result
- AIK
- 40%
- Draw
- 24% What happened
- Mjällby AIF
- 35%
Data coverage Both teams have the full 20-match model window available.
Projected vs produced
AIK produced 1.17 xG more than projected
Projected before kick-off Produced on the night
The shots behind it
- Shots
- 22
- 15
- On target
- 7
- 7
- Inside the box
- 16
- 10
- xG per shot
- 0.14
- 0.14
Recent form
1.71 xG created 2.99 xGA
1.64 xG created 2.11 xGA
xG created xG conceded (xGA) W / D / L: the match result
Head to head
Pre-match model & market record
4 opportunities flagged2 won2 lost
- Lost
- Won
- Won
- Lost
View pre-match record Hide pre-match record
| Selection | Price | Edge | Result |
|---|---|---|---|
| Over 2.5 goals | 1.70 | +29.7% | Lost |
| Both teams to score | 1.62 | +25.6% | Won |
| Over 1.5 goals | 1.20 | +11.0% | Won |
| Mjällby AIF to win | 3.10 | +9.8% | Lost |
Pre-match model vs market
| Outcome | Model | Market | Difference | Fair odds |
|---|---|---|---|---|
| AIK | 40.2% | 43.7% | −3.4 pp | 2.49 |
| Draw | 24.4% | 26.1% | −1.7 pp | 4.10 |
| Mjällby AIF | 35.4% | 30.3% | +5.1 pp | 2.82 |
Other markets
| Outcome | Model | Market | Difference | Fair odds |
|---|---|---|---|---|
| Both teams to score | 77.8% | 57.7% | +20.1 pp | 1.29 |
| Both teams not to score | 22.2% | 42.3% | −20.1 pp | 4.50 |
| Over 1.5 goals | 92.5% | 78.3% | +14.2 pp | 1.08 |
| Under 1.5 goals | 7.5% | 21.7% | −14.2 pp | 13.38 |
| Over 2.5 goals | 76.3% | 55.3% | +21.0 pp | 1.31 |
| Under 2.5 goals | 23.7% | 44.7% | −21.0 pp | 4.22 |
Prices and probabilities are the ones stored before kick-off; nothing here is recalculated. Edge is the model's probability times the price, minus one, 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)
- AIK sample
- 20 matches
- Mjällby AIF sample
- 20 matches
- Computed
- 9 hours before kick-off
- Prices taken
- 9 hours 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.