Home win
54.31%
Sporting Braga
POR1 · Primeira Liga · Match Analysis
Sporting Braga vs
Gil Vicente
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
26.51%
X
Away win
19.18%
Gil Vicente
Score model
Most likely scorelines.
Exact-score probabilities from the Poisson + Dixon-Coles goal model.
Additional scorelines
0:17.08%
3:05.85%
1:24.86%
3:14.80%
2:23.78%
Team context
Strength and recent form.
Venue-adjusted team strength, Elo rating and recent xG performance.
Home
Sporting Braga
Elo1580.3
Overall attack1.56
Overall defense1.02
Home attack1.69
Home defense0.85
Form signal+0.471
Last 5 xGF / xGA1.41 / 0.92
Last 10 xGF / xGA1.33 / 0.92
Last 10 xGD+0.42
League statusSTABLE · from POR1 2025/26
Away
Gil Vicente
Elo1504.8
Overall attack1.36
Overall defense1.10
Away attack1.26
Away defense1.39
Form signal-0.014
Last 5 xGF / xGA1.35 / 1.39
Last 10 xGF / xGA1.32 / 1.29
Last 10 xGD+0.03
League statusSTABLE · from POR1 2025/26
Elo difference
+75.5
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.
09.78%
121.00%
226.73%
320.79%
412.36%
55.88%
62.33%
7+1.11%
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
LeaguePOR1
Loaded teams26
Loaded historical matches1295
Target season2026/27
Previous seasons in history4
Season window2022/23 → 2023/24 → 2024/25 → 2025/26 → 2026/27
League tierTier 1
Historical league matches1295
xG matches377 / 1295
Effective xG matches300.69
Observed home xG1.43
Observed away xG1.22
Model home xG baseline1.40
Model away xG baseline1.25
Total league xG baseline2.65
Home-advantage weight0.719
Model configdata/models/POR1.json
Team attack half-life240.0 days
Team defense half-life240.0 days
Attack strength weight0.806
Defense strength weight1.194
Venue prior matches4.56
DistributionPoisson + Dixon-Coles
Dixon-Coles rho-0.044 (effective -0.044)
Dixon-Coles decay0.013
Goal overdispersion0.000
Implied goal variance H / A1.56 / 0.82
Relative strengths and form diagnostics
Sporting Braga
Home attack strength1.173
Home defense weakness0.736
Base lambda home1.46
Attack form xGF level1.386
Defense form xGA level (lower is better)0.915
Opponent-adjusted attack residual+0.043
Opponent-adjusted defense residual (higher is better)+0.388
Opponent-adjustment weight0.000
Model attack signal+0.062
Model defense signal+0.408
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD1.41 / 0.92 / +0.50
Last 10 xGF / xGA / xGD1.33 / 0.92 / +0.42
Gil Vicente
Away attack strength1.033
Away defense weakness0.930
Base lambda away0.89
Attack form xGF level1.341
Defense form xGA level (lower is better)1.354
Opponent-adjusted attack residual+0.041
Opponent-adjusted defense residual (higher is better)-0.002
Opponent-adjustment weight0.000
Model attack signal+0.017
Model defense signal-0.030
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD1.35 / 1.39 / -0.04
Last 10 xGF / xGA / xGD1.32 / 1.29 / +0.03
Historical data coverage
Sporting Braga
Total matches143
Home / away matches71 / 72
xG matches41 / 143
xG home / away coverage20 / 71 · 21 / 72
Effective total21.54
Effective attack / defense21.54 / 21.54
Effective home matches10.46
Effective home attack / defense10.46 / 10.46
Gil Vicente
Total matches143
Home / away matches72 / 71
xG matches41 / 143
xG home / away coverage21 / 72 · 20 / 71
Effective total21.42
Effective attack / defense21.42 / 21.42
Effective away matches10.26
Effective away attack / defense10.26 / 10.26
Historical data coverage
60.29%
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 1275 historical matches.
Positive improvement means the model performed better than the league baseline.
Total goals log-loss vs baseline+0.10%
1X2 log-loss vs baseline+7.93%
BTTS Brier vs baseline-0.79%
Over 2.5 Brier vs baseline+1.50%
Full backtest metrics
Model
MAE total goals1.2986
Exact score log-loss2.8981
Total goals Brier0.8236
Total goals log-loss1.8501
1X2 Brier0.5902
1X2 log-loss0.9893
BTTS Brier0.2545
Over 1.5 Brier0.1970
Over 2.5 Brier0.2467
Over 3.5 Brier0.2066
League baseline
MAE total goals1.3079
Exact score log-loss3.0072
Total goals Brier0.8251
Total goals log-loss1.8519
1X2 Brier0.6499
1X2 log-loss1.0745
BTTS Brier0.2525
Over 1.5 Brier0.1982
Over 2.5 Brier0.2505
Over 3.5 Brier0.2075
Calibration diagnostics
Home win · ECE 7.60%
0- 10% n=49 avg= 4.9% actual= 8.2% 10- 20% n=46 avg= 14.5% actual= 17.4% 20- 30% n=125 avg= 26.2% actual= 20.0% 30- 40% n=397 avg= 36.3% actual= 32.0% 40- 50% n=416 avg= 43.6% actual= 54.1% 50- 60% n=130 avg= 54.1% actual= 70.8% 60- 70% n=50 avg= 64.1% actual= 60.0% 70- 80% n=23 avg= 75.5% actual= 73.9% 80- 90% n=23 avg= 85.8% actual= 82.6% 90-100% n=16 avg= 92.5% actual= 87.5%
Draw · ECE 1.67%
0- 10% n=45 avg= 7.2% actual= 15.6% 10- 20% n=72 avg= 15.1% actual= 13.9% 20- 30% n=1129 avg= 26.3% actual= 24.8% 30- 40% n=29 avg= 31.5% actual= 31.0%
Away win · ECE 5.40%
0- 10% n=59 avg= 4.4% actual= 0.0% 10- 20% n=96 avg= 15.9% actual= 14.6% 20- 30% n=292 avg= 26.0% actual= 19.2% 30- 40% n=559 avg= 34.1% actual= 31.7% 40- 50% n=144 avg= 44.5% actual= 59.0% 50- 60% n=48 avg= 53.5% actual= 50.0% 60- 70% n=24 avg= 64.1% actual= 41.7% 70- 80% n=23 avg= 75.2% actual= 78.3% 80- 90% n=23 avg= 85.9% actual= 87.0% 90-100% n=7 avg= 93.2% actual= 57.1%
BTTS · ECE 6.34%
20- 30% n=18 avg= 28.3% actual= 44.4% 30- 40% n=87 avg= 36.0% actual= 51.7% 40- 50% n=145 avg= 44.6% actual= 49.0% 50- 60% n=1005 avg= 54.1% actual= 48.9% 60- 70% n=20 avg= 63.7% actual= 35.0%
Over 2.5 · ECE 3.21%
20- 30% n=9 avg= 27.7% actual= 22.2% 30- 40% n=51 avg= 36.4% actual= 49.0% 40- 50% n=774 avg= 48.7% actual= 47.3% 50- 60% n=337 avg= 52.5% actual= 58.5% 60- 70% n=64 avg= 64.8% actual= 62.5% 70- 80% n=34 avg= 74.1% actual= 70.6% 80- 90% n=6 avg= 82.9% actual= 83.3%
Walk-forward - latest periods
| Period | N | Model 1X2 LL | Baseline 1X2 LL | Improvement |
|---|---|---|---|---|
| 2025-09 | 29 | 0.9643 | 1.0870 | +11.29% |
| 2025-10 | 19 | 0.8905 | 1.0650 | +16.38% |
| 2025-11 | 25 | 0.8874 | 1.1337 | +21.73% |
| 2025-12 | 35 | 0.9261 | 1.0949 | +15.42% |
| 2026-01 | 33 | 0.8027 | 1.0414 | +22.91% |
| 2026-02 | 37 | 0.9087 | 1.0392 | +12.55% |
| 2026-03 | 29 | 1.0067 | 1.1369 | +11.45% |
| 2026-04 | 38 | 1.0082 | 1.0736 | +6.10% |
| 2026-05 | 27 | 1.1695 | 1.0936 | -6.95% |
| 2026-08 | 33 | 0.9132 | 1.0810 | +15.52% |
| 2026-09 | 29 | 1.0468 | 1.1104 | +5.73% |
| 2026-10 | 9 | 0.6873 | 1.0362 | +33.67% |
Football is data.
NILYTIX turns match data into transparent model probabilities and measurable analytical signals.