Saturday, 12/09/2026 at 18:00
Full timeFF Jaro 1:1 SJK
SJK were the model's likeliest winner before kick-off at 43%. It finished 1–1.
The model against the result
- FF Jaro
- 30%
- Draw
- 28% What happened
- SJK
- 43%
Data coverage Both teams have the full 20-match model window available.
Recent form
xG created xG conceded (xGA) W / D / L: the match result
Head to head
Pre-match model & market record
6 opportunities flagged3 won3 lost
- Lost
- Lost
- Won
- Won
- Won
- Lost
View pre-match record Hide pre-match record
| Selection | Price | Edge | Result |
|---|---|---|---|
| Over 2.5 goals | 1.85 | +15.6% | Lost |
| FF Jaro 2+ goals | 2.63 | +12.3% | Lost |
| Both teams to score | 1.62 | +9.6% | Won |
| Over 1.5 goals | 1.25 | +7.2% | Won |
| FF Jaro to score | 1.33 | +4.9% | Won |
| SJK 2+ goals | 1.91 | +0.5% | Lost |
Pre-match model vs market
| Outcome | Model | Market | Difference | Fair odds |
|---|---|---|---|---|
| FF Jaro | 29.7% | 28.5% | +1.3 pp | 3.36 |
| Draw | 27.6% | 26.4% | +1.2 pp | 3.62 |
| SJK | 42.7% | 45.1% | −2.4 pp | 2.34 |
Other markets
| Outcome | Model | Market | Difference | Fair odds |
|---|---|---|---|---|
| FF Jaro to score | 78.7% | 70.9% | +7.8 pp | 1.27 |
| FF Jaro not to score | 21.3% | 29.1% | −7.8 pp | 4.70 |
| SJK to score | 84.3% | 79.2% | +5.1 pp | 1.19 |
| SJK not to score | 15.7% | 20.8% | −5.1 pp | 6.37 |
| Both teams to score | 67.8% | 57.7% | +10.2 pp | 1.47 |
| Both teams not to score | 32.2% | 42.3% | −10.2 pp | 3.11 |
| FF Jaro 2+ goals | 42.8% | 35.5% | +7.3 pp | 2.34 |
| FF Jaro at most 1 goal | 57.2% | 64.5% | −7.3 pp | 1.75 |
| SJK 2+ goals | 52.6% | 48.5% | +4.1 pp | 1.90 |
| SJK at most 1 goal | 47.4% | 51.5% | −4.1 pp | 2.11 |
| Over 1.5 goals | 85.8% | 75.0% | +10.8 pp | 1.17 |
| Under 1.5 goals | 14.2% | 25.0% | −10.8 pp | 7.02 |
| Over 2.5 goals | 62.5% | 51.3% | +11.2 pp | 1.60 |
| Under 2.5 goals | 37.5% | 48.7% | −11.2 pp | 2.67 |
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)
- FF Jaro sample
- 20 matches
- SJK sample
- 20 matches
- Computed
- 3 hours before kick-off
- Prices taken
- 3 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.