Home win
9.50%
FC Augsburg
GER1 · Bundesliga · Match Analysis
FC Augsburg vs
Bayern Munich
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
14.86%
X
Away win
75.64%
Bayern Munich
Score model
Most likely scorelines.
Exact-score probabilities from the Poisson + Dixon-Coles goal model.
Additional scorelines
1:16.16%
0:45.80%
0:14.40%
2:34.39%
2:24.37%
Team context
Strength and recent form.
Venue-adjusted team strength, Elo rating and recent xG performance.
Home
FC Augsburg
Elo1505.9
Overall attack1.38
Overall defense1.87
Home attack1.50
Home defense1.59
Form signal-1.017
Last 5 xGF / xGA1.46 / 2.65
Last 10 xGF / xGA1.66 / 2.36
Last 10 xGD-0.70
League statusSTABLE · from GER1 2025/26
Away
Bayern Munich
Elo1694.3
Overall attack2.83
Overall defense1.10
Away attack2.46
Away defense1.23
Form signal+2.328
Last 5 xGF / xGA3.13 / 0.61
Last 10 xGF / xGA3.02 / 1.06
Last 10 xGD+1.97
League statusSTABLE · from GER1 2025/26
Elo difference
-188.4
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.
02.41%
15.50%
214.81%
319.16%
419.53%
515.92%
610.82%
7+11.85%
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
LeagueGER1
Loaded teams25
Loaded historical matches1260
Target season2026/27
Previous seasons in history4
Season window2022/23 → 2023/24 → 2024/25 → 2025/26 → 2026/27
League tierTier 1
Historical league matches1260
xG matches1258 / 1260
Effective xG matches634.05
Observed home xG1.73
Observed away xG1.35
Model home xG baseline1.73
Model away xG baseline1.35
Total league xG baseline3.08
Home-advantage weight1.000
Model configdata/models/GER1.json
Team attack half-life240.0 days
Team defense half-life240.0 days
Attack strength weight1.000
Defense strength weight1.000
Venue prior matches0.00
DistributionPoisson + Dixon-Coles
Dixon-Coles rho-0.130 (effective -0.130)
Dixon-Coles decay0.000
Goal overdispersion0.000
Implied goal variance H / A1.07 / 3.01
Relative strengths and form diagnostics
FC Augsburg
Home attack strength0.903
Home defense weakness1.132
Base lambda home1.23
Attack form xGF level1.531
Defense form xGA level (lower is better)2.548
Opponent-adjusted attack residual+0.022
Opponent-adjusted defense residual (higher is better)-0.977
Opponent-adjustment weight0.000
Model attack signal-0.010
Model defense signal-1.007
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD1.46 / 2.65 / -1.19
Last 10 xGF / xGA / xGD1.66 / 2.36 / -0.70
Bayern Munich
Away attack strength1.606
Away defense weakness0.785
Base lambda away2.45
Attack form xGF level3.094
Defense form xGA level (lower is better)0.766
Opponent-adjusted attack residual+1.426
Opponent-adjusted defense residual (higher is better)+0.660
Opponent-adjustment weight0.000
Model attack signal+1.500
Model defense signal+0.776
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD3.13 / 0.61 / +2.52
Last 10 xGF / xGA / xGD3.02 / 1.06 / +1.97
Historical data coverage
FC Augsburg
Total matches140
Home / away matches70 / 70
xG matches140 / 140
xG home / away coverage70 / 70 · 70 / 70
Effective total27.54
Effective attack / defense27.54 / 27.54
Effective home matches13.61
Effective home attack / defense13.61 / 13.61
Bayern Munich
Total matches140
Home / away matches70 / 70
xG matches140 / 140
xG home / away coverage70 / 70 · 70 / 70
Effective total27.54
Effective attack / defense27.54 / 27.54
Effective away matches13.83
Effective away attack / defense13.83 / 13.83
Historical data coverage
84.27%
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 1240 historical matches.
Positive improvement means the model performed better than the league baseline.
Total goals log-loss vs baseline+0.85%
1X2 log-loss vs baseline+7.69%
BTTS Brier vs baseline+0.53%
Over 2.5 Brier vs baseline+1.45%
Full backtest metrics
Model
MAE total goals1.4041
Exact score log-loss3.1095
Total goals Brier0.8396
Total goals log-loss1.9621
1X2 Brier0.5907
1X2 log-loss0.9917
BTTS Brier0.2393
Over 1.5 Brier0.1367
Over 2.5 Brier0.2346
Over 3.5 Brier0.2396
League baseline
MAE total goals1.4083
Exact score log-loss3.2426
Total goals Brier0.8427
Total goals log-loss1.9790
1X2 Brier0.6500
1X2 log-loss1.0743
BTTS Brier0.2405
Over 1.5 Brier0.1377
Over 2.5 Brier0.2380
Over 3.5 Brier0.2471
Calibration diagnostics
Home win · ECE 2.66%
0- 10% n=13 avg= 8.2% actual= 7.7% 10- 20% n=66 avg= 16.4% actual= 13.6% 20- 30% n=141 avg= 25.6% actual= 22.7% 30- 40% n=293 avg= 35.1% actual= 34.5% 40- 50% n=296 avg= 44.8% actual= 42.2% 50- 60% n=215 avg= 54.3% actual= 52.6% 60- 70% n=126 avg= 64.2% actual= 72.2% 70- 80% n=65 avg= 74.5% actual= 78.5% 80- 90% n=24 avg= 83.9% actual= 83.3% 90-100% n=1 avg= 92.9% actual= 0.0%
Draw · ECE 0.49%
0- 10% n=8 avg= 8.5% actual= 12.5% 10- 20% n=131 avg= 16.4% actual= 16.8% 20- 30% n=1019 avg= 26.0% actual= 25.9% 30- 40% n=82 avg= 31.0% actual= 25.6%
Away win · ECE 2.84%
0- 10% n=69 avg= 7.0% actual= 5.8% 10- 20% n=228 avg= 15.6% actual= 11.8% 20- 30% n=367 avg= 24.8% actual= 26.4% 30- 40% n=310 avg= 34.9% actual= 37.4% 40- 50% n=143 avg= 44.4% actual= 50.3% 50- 60% n=73 avg= 54.6% actual= 52.1% 60- 70% n=31 avg= 64.1% actual= 67.7% 70- 80% n=18 avg= 74.3% actual= 72.2% 80- 90% n=1 avg= 83.2% actual=100.0%
BTTS · ECE 1.73%
40- 50% n=78 avg= 47.7% actual= 53.8% 50- 60% n=731 avg= 55.8% actual= 57.9% 60- 70% n=421 avg= 63.3% actual= 63.2% 70- 80% n=10 avg= 71.3% actual= 80.0%
Over 2.5 · ECE 4.57%
30- 40% n=20 avg= 38.1% actual= 45.0% 40- 50% n=204 avg= 46.5% actual= 53.9% 50- 60% n=570 avg= 55.2% actual= 60.5% 60- 70% n=349 avg= 64.1% actual= 66.2% 70- 80% n=86 avg= 73.5% actual= 75.6% 80- 90% n=11 avg= 83.0% actual= 72.7%
Walk-forward - latest periods
| Period | N | Model 1X2 LL | Baseline 1X2 LL | Improvement |
|---|---|---|---|---|
| 2025-08 | 18 | 1.0297 | 1.0924 | +5.74% |
| 2025-09 | 27 | 0.9245 | 1.0913 | +15.28% |
| 2025-10 | 28 | 0.8452 | 1.0420 | +18.89% |
| 2025-11 | 35 | 0.9943 | 1.0574 | +5.97% |
| 2025-12 | 27 | 1.0225 | 1.0710 | +4.53% |
| 2026-01 | 42 | 1.0110 | 1.0821 | +6.57% |
| 2026-02 | 35 | 0.9224 | 1.0167 | +9.27% |
| 2026-03 | 31 | 0.9132 | 1.0955 | +16.64% |
| 2026-04 | 36 | 0.9794 | 1.1201 | +12.56% |
| 2026-05 | 27 | 1.0991 | 1.0685 | -2.86% |
| 2026-08 | 9 | 0.8011 | 0.9156 | +12.51% |
| 2026-09 | 27 | 0.9461 | 1.0655 | +11.21% |
Football is data.
NILYTIX turns match data into transparent model probabilities and measurable analytical signals.