Football Data Intelligence
Back to NILYTIX
GER1 · Bundesliga · Match Analysis

VfB Stuttgart vs
Borussia Dortmund

Model-based match probabilities derived from multi-season xG data, team strength, venue performance, recent form, Elo ratings and league context.

Analysis date19 Sep 2026
Target season2026/27
History window5 seasons
League tierTier 1
Model output

Match probabilities.

Probabilities are model estimates, not certainties or betting guarantees.

Home win
38.68%
VfB Stuttgart
Draw
26.45%
X
Away win
34.87%
Borussia Dortmund
Expected goals 1.61 – 1.52 3.14 total
BTTS 64.00% Both teams to score
Over 1.5 83.42% 2+ total goals
Over 2.5 60.66% 3+ total goals
Score model

Most likely scorelines.

Exact-score probabilities from the Poisson + Dixon-Coles goal model.

#11:112.06%
#22:18.61%
#31:28.13%
#42:26.56%
#50:05.73%
Additional scorelines
2:05.65%
1:05.62%
0:15.23%
0:25.05%
3:14.62%
Team context

Strength and recent form.

Venue-adjusted team strength, Elo rating and recent xG performance.

Home

VfB Stuttgart

Elo1557.6
Overall attack1.87
Overall defense1.79
Home attack2.15
Home defense1.29
Form signal-0.486
Last 5 xGF / xGA2.19 / 2.70
Last 10 xGF / xGA2.08 / 2.51
Last 10 xGD-0.44
League statusSTABLE · from GER1 2025/26
Away

Borussia Dortmund

Elo1625.7
Overall attack1.89
Overall defense1.17
Away attack1.48
Away defense1.36
Form signal+0.902
Last 5 xGF / xGA1.96 / 0.95
Last 10 xGF / xGA1.79 / 1.08
Last 10 xGD+0.71
League statusSTABLE · from GER1 2025/26
Elo difference
-68.1

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.

H2H matches8Effective: 2.35
Average goals3.75VfB Stuttgart 1.85 · Borussia Dortmund 1.90
H2H 3+ goals61.30%Historical context
H2H BTTS58.48%Model BTTS: 64.00%
H2H 2+ goals92.24%
H2H 3+ goals61.30%
H2H 4+ goals41.50%
H2H BTTS58.48%
Goal distribution

Total goals profile.

The model's probability distribution for the total number of goals.

05.73%
110.85%
222.76%
322.34%
417.51%
510.98%
65.74%
7+4.08%
0–1 goals16.58%Low total
2+ goals83.42%Over 1.5
3+ goals60.66%Over 2.5
4+ goals38.32%Over 3.5
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 matches1251
Target season2026/27
Previous seasons in history4
Season window2022/23 → 2023/24 → 2024/25 → 2025/26 → 2026/27
League tierTier 1
Historical league matches1251
xG matches333 / 1251
Effective xG matches267.16
Observed home xG1.81
Observed away xG1.39
Model home xG baseline1.81
Model away xG baseline1.39
Total league xG baseline3.20
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 / A1.61 / 1.52
Relative strengths and form diagnostics

VfB Stuttgart

Home attack strength1.120
Home defense weakness0.952
Base lambda home1.70
Attack form xGF level2.147
Defense form xGA level (lower is better)2.634
Opponent-adjusted attack residual+0.584
Opponent-adjusted defense residual (higher is better)-0.992
Opponent-adjustment weight0.000
Model attack signal+0.546
Model defense signal-1.033
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD2.19 / 2.70 / -0.51
Last 10 xGF / xGA / xGD2.08 / 2.51 / -0.44

Borussia Dortmund

Away attack strength1.041
Away defense weakness0.836
Base lambda away1.38
Attack form xGF level1.898
Defense form xGA level (lower is better)0.996
Opponent-adjusted attack residual+0.198
Opponent-adjusted defense residual (higher is better)+0.510
Opponent-adjustment weight0.000
Model attack signal+0.297
Model defense signal+0.605
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD1.96 / 0.95 / +1.01
Last 10 xGF / xGA / xGD1.79 / 1.08 / +0.71
Historical data coverage

VfB Stuttgart

Total matches139
Home / away matches69 / 70
xG matches37 / 139
xG home / away coverage18 / 69 · 19 / 70
Effective total19.67
Effective attack / defense19.67 / 19.67
Effective home matches9.43
Effective home attack / defense9.43 / 9.43

Borussia Dortmund

Total matches139
Home / away matches70 / 69
xG matches37 / 139
xG home / away coverage19 / 70 · 18 / 69
Effective total19.65
Effective attack / defense19.65 / 19.65
Effective away matches9.27
Effective away attack / defense9.27 / 9.27
Historical data coverage
54.74%

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 1231 historical matches.

Positive improvement means the model performed better than the league baseline.

Total goals log-loss vs baseline+0.25%
1X2 log-loss vs baseline+3.06%
BTTS Brier vs baseline-0.60%
Over 2.5 Brier vs baseline+0.41%
Full backtest metrics
Model
MAE total goals1.4509
Exact score log-loss3.2237
Total goals Brier0.8463
Total goals log-loss2.0018
1X2 Brier0.6283
1X2 log-loss1.0450
BTTS Brier0.2443
Over 1.5 Brier0.1415
Over 2.5 Brier0.2458
Over 3.5 Brier0.2542
League baseline
MAE total goals1.4546
Exact score log-loss3.2737
Total goals Brier0.8476
Total goals log-loss2.0068
1X2 Brier0.6521
1X2 log-loss1.0779
BTTS Brier0.2428
Over 1.5 Brier0.1414
Over 2.5 Brier0.2468
Over 3.5 Brier0.2571
Calibration diagnostics
Home win · ECE 7.81%
 0- 10%  n=2    avg=  8.3% actual=  0.0%
10- 20%  n=18   avg= 15.2% actual=  5.6%
20- 30%  n=47   avg= 25.8% actual= 25.5%
30- 40%  n=299  avg= 37.6% actual= 27.1%
40- 50%  n=764  avg= 42.3% actual= 49.6%
50- 60%  n=46   avg= 54.0% actual= 54.3%
60- 70%  n=35   avg= 64.7% actual= 71.4%
70- 80%  n=16   avg= 74.0% actual= 87.5%
80- 90%  n=4    avg= 83.1% actual= 25.0%
Draw · ECE 3.58%
 0- 10%  n=1    avg=  9.8% actual=100.0%
10- 20%  n=37   avg= 16.7% actual= 16.2%
20- 30%  n=1177 avg= 28.3% actual= 24.8%
30- 40%  n=16   avg= 30.9% actual= 43.8%
Away win · ECE 7.47%
 0- 10%  n=16   avg=  7.9% actual= 18.8%
10- 20%  n=55   avg= 15.0% actual= 18.2%
20- 30%  n=602  avg= 28.1% actual= 21.6%
30- 40%  n=475  avg= 32.1% actual= 41.9%
40- 50%  n=46   avg= 44.1% actual= 45.7%
50- 60%  n=21   avg= 53.8% actual= 57.1%
60- 70%  n=9    avg= 64.8% actual= 77.8%
70- 80%  n=7    avg= 73.2% actual= 71.4%
BTTS · ECE 4.29%
30- 40%  n=6    avg= 35.8% actual=100.0%
40- 50%  n=14   avg= 47.7% actual= 64.3%
50- 60%  n=1074 avg= 55.4% actual= 59.2%
60- 70%  n=125  avg= 63.7% actual= 60.8%
70- 80%  n=12   avg= 71.7% actual= 58.3%
Over 2.5 · ECE 9.99%
30- 40%  n=6    avg= 38.6% actual= 66.7%
40- 50%  n=783  avg= 49.2% actual= 60.2%
50- 60%  n=313  avg= 52.7% actual= 62.9%
60- 70%  n=90   avg= 63.8% actual= 65.6%
70- 80%  n=34   avg= 73.8% actual= 79.4%
80- 90%  n=5    avg= 83.4% actual= 80.0%
Walk-forward - latest periods
Period N Model 1X2 LL Baseline 1X2 LL Improvement
2025-08 18 1.2312 1.2582 +2.15%
2025-09 27 0.9969 1.0627 +6.20%
2025-10 28 0.9379 1.0588 +11.42%
2025-11 35 1.0160 1.0735 +5.35%
2025-12 27 1.0299 1.0723 +3.96%
2026-01 42 1.0001 1.0852 +7.84%
2026-02 35 0.9390 1.0213 +8.05%
2026-03 31 0.9570 1.0960 +12.69%
2026-04 36 0.9815 1.1214 +12.48%
2026-05 27 1.0897 1.0695 -1.89%
2026-08 9 0.7945 0.8989 +11.61%
2026-09 18 0.9847 1.0927 +9.88%

Football is data.

NILYTIX turns match data into transparent model probabilities and measurable analytical signals.

Back to Matches Follow on X