Hajduk Split v Dinamo Zagreb — Prediction, Odds & Stats
Saturday 10 October 2026 · CRO-HNL · 2627
CRO-HNL
results-only Prediction generated
AI prediction
ai-blend v1.0 dailyRaw model output; no calibration record for this fixture's bands yet.
Top 5 scorelines
- 1-1 12.3%
- 1-2 9.8%
- 0-2 8.4%
- 0-1 6.7%
- 0-0 6.6%
Goals
| Over 2.5 | 59.6% | Under 2.5 | 40.4% |
| BTTS yes | 60.8% | BTTS no | 39.2% |
| Hajduk Split 1+ | 68.9% | Hajduk Split 2+ | 32.6% |
| Dinamo Zagreb 1+ | 85.3% | Dinamo Zagreb 2+ | 57.1% |
Expected goals 1.17 – 1.92. Every market above is read off one scoreline distribution.
Footing
Positive factors
- Nothing in the data singles out Dinamo Zagreb.
Risk factors
- Data quality is 20/100, so this price rests on less than the model would like.
- Hajduk Split have only 1 matches on record.
- Dinamo Zagreb have only 9 matches on record.
Why the model thinks this
The price
Dinamo Zagreb have an estimated 52.8% win probability, against 26.3% for the draw and 21.0% for Hajduk Split. Expected goals from the ensemble are 1.17 for Hajduk Split and 1.92 for Dinamo Zagreb.
Why Hajduk Split
Form is good: 3.00 points a match from the last five. At home Hajduk Split average 1.35 xG a match.
Why the draw is live
The draw sits at 26.3%.
Why Dinamo Zagreb can win
Nothing in the data singles out Dinamo Zagreb.
Key players
No player-level data for this fixture; the leagues with lineups are the big five.
Availability
No lineup on record for Hajduk Split, so availability is unknown. No lineup on record for Dinamo Zagreb, so availability is unknown.
The matchup, as far as the data reaches
Hajduk Split: 50% possession, 12.0 shots a match, 12.0 faced, 0.30 xG a match from set pieces. Dinamo Zagreb: 36% possession, 9.2 shots a match, 14.8 faced, 0.30 xG a match from set pieces.
Inputs last refreshed: matches 2026-09-11 15:19 · team_stats 2026-09-11 06:03 · availability 2026-09-11 15:38 · prediction 2026-09-10 19:28 ·
Dinamo Zagreb are the model's most likely outcome at 52.8%. The likeliest scoreline is 1-1 at 12.3%. Confidence 22/100, data quality 20/100. These are probabilities, not certainties: the less likely outcome happens as often as its number says.
Written from the numbers the model saw, not by a language model; nothing here is a statistic the snapshot does not hold. How predictions work.
Was this pick made in advance?
-oos is out of sample: it was fitted only on matches
played before this one, so its pick is a genuine forecast rather than hindsight.
Anything without that suffix was fitted on all available data.What the model said
| Model | Home / Draw / Away | Expected goals | Likeliest score | O2.5 | BTTS |
|---|---|---|---|---|---|
| ai-blend | 1.17–1.92 | 0% | 0% | 0% | |
| dc-xg | 1.09–1.84 | 1-1 13% | 56% | 58% |
A model whose name ends -oos was produced by the walk-forward backtest:
it was fitted only on matches played before this one, so the pick is genuinely out of sample.