Track Record
How the model actually performs on Greek Super League matches • Predictions through: 2026-10-10 08:33:32
Matches evaluated
42
finished matches with a stored prediction
Pick accuracy
52.4%
most likely outcome was correct
Log loss
0.951
uniform guess = 1.099 — lower is better
Brier score
0.560
0 = perfect, lower is better
Probability calibration
When the model says 60%, the event should happen about 60% of the time. The dashed line is perfection; the solid line is the model across all three outcomes.
Overall reliability curve, all three outcomes pooled. Sparse buckets (few matches) naturally wobble more — the current sample is small this early in the season.
Per-outcome diagnostics
| Outcome | Precision | Recall | F1 | Matches |
|---|---|---|---|---|
| Home win | 61% | 70% | 65% | 20 |
| Draw | 0% | 0% | 0% | 9 |
| Away win | 44% | 62% | 52% | 13 |
Draws are the hardest outcome in football — precision/recall stay low for every honest model.
Latest results
| Date | Match | Pick | Result | |
|---|---|---|---|---|
| 2026-10-12 | PAOK FC – Kalamata FC | Home win (65.5%) | 1–3 | ✗ |
| 2026-10-11 | Olympiacos FC – Panathinaikos FC | Away win (45.4%) | 1–0 | ✗ |
| 2026-10-11 | Kifisia FC – Panetolikos FC | Away win (37.1%) | 2–0 | ✗ |
| 2026-10-11 | Iraklis FC – Levadiakos FC | Away win (38.0%) | 2–0 | ✗ |
| 2026-10-11 | Aris Thessaloniki FC – Volos NFC | Home win (51.6%) | 3–2 | ✓ |
| 2026-10-10 | Asteras Tripolis FC – Atromitos FC | Draw (39.1%) | 2–1 | ✗ |
| 2026-10-10 | AEK Athens FC – OFI Crete FC | Home win (65.9%) | 3–0 | ✓ |
| 2026-09-20 | Volos NFC – AEK Athens FC | Away win (57.1%) | 1–2 | ✓ |
| 2026-09-20 | Panetolikos FC – PAOK FC | Away win (57.4%) | 1–3 | ✓ |
| 2026-09-20 | OFI Crete FC – Asteras Tripolis FC | Away win (41.9%) | 2–2 | ✗ |
| 2026-09-20 | Levadiakos FC – Olympiacos FC | Away win (47.1%) | 0–1 | ✓ |
| 2026-09-20 | Kalamata FC – Panathinaikos FC | Away win (59.4%) | 0–1 | ✓ |
What we don't publish: betting simulations, ROI figures or “value picks”. The numbers above are about the quality of the probabilities, not about wagering — see the methodology for how they are produced.