Home win
22.85%
SC Cambuur
NED1 · Eredivisie · Match Analysis
SC Cambuur vs
AZ
Model-based match probabilities derived from multi-season xG data, team strength, venue performance, recent form, Elo ratings and league context.
Model output
Match probabilities.
Probabilities are model estimates, not certainties or betting guarantees.
Draw
21.99%
X
Away win
55.16%
AZ
Score model
Most likely scorelines.
Exact-score probabilities from the NB2 + Dixon-Coles goal model.
Additional scorelines
0:15.87%
2:15.72%
0:35.05%
2:34.31%
0:04.18%
Team context
Strength and recent form.
Venue-adjusted team strength, Elo rating and recent xG performance.
Home
SC Cambuur
Elo1441.2
Overall attack1.37
Overall defense1.90
Home attack1.44
Home defense2.00
Form signal-0.228
Last 5 xGF / xGA1.38 / 1.54
Last 10 xGF / xGA1.38 / 1.73
Last 10 xGD-0.35
League statusSTABLE · from NED1 2022/23
Away
AZ
Elo1580.8
Overall attack2.01
Overall defense1.26
Away attack1.81
Away defense1.47
Form signal+0.647
Last 5 xGF / xGA1.91 / 1.37
Last 10 xGF / xGA2.13 / 1.28
Last 10 xGD+0.85
League statusSTABLE · from NED1 2025/26
Elo difference
-139.6
Elo is one input among several and does not determine the final 1X2 probability on its own.
Head-to-head
Historical matchup context.
H2H values provide context and are not used as a standalone prediction.
Goal distribution
Total goals profile.
The model's probability distribution for the total number of goals.
04.18%
19.25%
219.25%
321.08%
418.35%
512.98%
67.77%
7+7.14%
Technical detail
How the model reached the estimate.
Detailed diagnostics are kept below the headline probabilities so the public report remains readable.
League baseline and model setup
LeagueNED1
Loaded teams25
Loaded historical matches1296
Target season2026/27
Previous seasons in history4
Season window2022/23 → 2023/24 → 2024/25 → 2025/26 → 2026/27
League tierTier 1
Historical league matches1296
xG matches378 / 1296
Effective xG matches300.50
Observed home xG1.78
Observed away xG1.44
Model home xG baseline1.82
Model away xG baseline1.41
Total league xG baseline3.22
Home-advantage weight1.238
Model configdata/models/NED1.json
Team attack half-life240.0 days
Team defense half-life240.0 days
Attack strength weight1.012
Defense strength weight0.828
Venue prior matches0.00
DistributionNB2 + Dixon-Coles
Dixon-Coles rho-0.095 (effective -0.093)
Dixon-Coles decay0.028
Goal overdispersion0.031
Implied goal variance H / A1.40 / 2.32
Relative strengths and form diagnostics
SC Cambuur
Home attack strength0.938
Home defense weakness1.129
Base lambda home1.55
Attack form xGF level1.381
Defense form xGA level (lower is better)1.609
Opponent-adjusted attack residual-0.144
Opponent-adjusted defense residual (higher is better)+0.087
Opponent-adjustment weight0.000
Model attack signal-0.230
Model defense signal+0.002
Opponent blend0.000
Form matches 5 / 105 / 8
Last 5 xGF / xGA / xGD1.38 / 1.54 / -0.16
Last 10 xGF / xGA / xGD1.38 / 1.73 / -0.35
AZ
Away attack strength1.154
Away defense weakness0.896
Base lambda away1.80
Attack form xGF level1.984
Defense form xGA level (lower is better)1.337
Opponent-adjusted attack residual+0.326
Opponent-adjusted defense residual (higher is better)+0.235
Opponent-adjustment weight0.000
Model attack signal+0.373
Model defense signal+0.274
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD1.91 / 1.37 / +0.54
Last 10 xGF / xGA / xGD2.13 / 1.28 / +0.85
Historical data coverage
SC Cambuur
Total matches42
Home / away matches21 / 21
xG matches8 / 42
xG home / away coverage4 / 21 · 4 / 21
Effective total7.05
Effective attack / defense7.05 / 7.05
Effective home matches3.43
Effective home attack / defense3.43 / 3.43
AZ
Total matches144
Home / away matches72 / 72
xG matches42 / 144
xG home / away coverage21 / 72 · 21 / 72
Effective total22.11
Effective attack / defense22.11 / 22.11
Effective away matches10.91
Effective away attack / defense10.91 / 10.91
Historical data coverage
28.78%
This measures usable historical evidence. It is not the probability that the prediction is correct.
Validation
Historical model performance.
Leakage-safe backtesting compares the fitted model with a league baseline over 1276 historical matches.
Positive improvement means the model performed better than the league baseline.
Total goals log-loss vs baseline+0.66%
1X2 log-loss vs baseline+6.39%
BTTS Brier vs baseline-0.04%
Over 2.5 Brier vs baseline+1.28%
Full backtest metrics
Model
MAE total goals1.3977
Exact score log-loss3.1300
Total goals Brier0.8380
Total goals log-loss1.9536
1X2 Brier0.6010
1X2 log-loss1.0049
BTTS Brier0.2427
Over 1.5 Brier0.1404
Over 2.5 Brier0.2431
Over 3.5 Brier0.2432
League baseline
MAE total goals1.4089
Exact score log-loss3.2374
Total goals Brier0.8400
Total goals log-loss1.9665
1X2 Brier0.6494
1X2 log-loss1.0734
BTTS Brier0.2426
Over 1.5 Brier0.1421
Over 2.5 Brier0.2463
Over 3.5 Brier0.2471
Calibration diagnostics
Home win · ECE 6.54%
0- 10% n=5 avg= 9.0% actual= 20.0% 10- 20% n=28 avg= 16.8% actual= 14.3% 20- 30% n=101 avg= 26.3% actual= 19.8% 30- 40% n=290 avg= 36.1% actual= 23.8% 40- 50% n=546 avg= 44.5% actual= 48.5% 50- 60% n=175 avg= 54.3% actual= 62.9% 60- 70% n=75 avg= 64.0% actual= 65.3% 70- 80% n=37 avg= 74.3% actual= 70.3% 80- 90% n=19 avg= 84.0% actual= 84.2%
Draw · ECE 1.58%
0- 10% n=8 avg= 8.7% actual= 25.0% 10- 20% n=92 avg= 16.6% actual= 21.7% 20- 30% n=1176 avg= 26.6% actual= 25.4%
Away win · ECE 7.41%
0- 10% n=39 avg= 6.9% actual= 2.6% 10- 20% n=152 avg= 16.1% actual= 13.8% 20- 30% n=528 avg= 26.0% actual= 19.7% 30- 40% n=376 avg= 33.7% actual= 44.7% 40- 50% n=113 avg= 44.0% actual= 53.1% 50- 60% n=42 avg= 54.2% actual= 52.4% 60- 70% n=21 avg= 64.8% actual= 76.2% 70- 80% n=4 avg= 75.8% actual= 50.0% 80- 90% n=1 avg= 80.1% actual=100.0%
BTTS · ECE 2.40%
40- 50% n=34 avg= 47.8% actual= 50.0% 50- 60% n=1076 avg= 53.9% actual= 56.2% 60- 70% n=156 avg= 63.6% actual= 65.4% 70- 80% n=10 avg= 72.2% actual= 90.0%
Over 2.5 · ECE 7.60%
40- 50% n=657 avg= 48.9% actual= 56.8% 50- 60% n=390 avg= 53.5% actual= 63.8% 60- 70% n=153 avg= 64.4% actual= 63.4% 70- 80% n=66 avg= 73.4% actual= 69.7% 80- 90% n=10 avg= 83.2% actual= 90.0%
Walk-forward - latest periods
| Period | N | Model 1X2 LL | Baseline 1X2 LL | Improvement |
|---|---|---|---|---|
| 2025-09 | 29 | 0.9490 | 1.0452 | +9.20% |
| 2025-10 | 28 | 0.8736 | 1.0587 | +17.48% |
| 2025-11 | 34 | 1.0856 | 1.0480 | -3.58% |
| 2025-12 | 27 | 0.9866 | 1.1128 | +11.34% |
| 2026-01 | 30 | 1.1591 | 1.1345 | -2.17% |
| 2026-02 | 38 | 1.0177 | 1.0729 | +5.15% |
| 2026-03 | 32 | 1.0199 | 1.0455 | +2.44% |
| 2026-04 | 27 | 0.8740 | 1.0770 | +18.85% |
| 2026-05 | 27 | 1.0036 | 1.1111 | +9.67% |
| 2026-08 | 33 | 1.0228 | 1.1116 | +8.00% |
| 2026-09 | 30 | 1.0074 | 1.1451 | +12.03% |
| 2026-10 | 9 | 1.0607 | 1.1531 | +8.01% |
Football is data.
NILYTIX turns match data into transparent model probabilities and measurable analytical signals.