Football Data Intelligence
Back to NILYTIX
ENG1 · Premier League · Match Analysis

Manchester City vs
Sunderland

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

Analysis date20 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
64.10%
Manchester City
Draw
22.09%
X
Away win
13.80%
Sunderland
Expected goals 2.13 – 0.91 3.03 total
BTTS 53.79% Both teams to score
Over 1.5 81.81% 2+ total goals
Over 2.5 58.46% 3+ total goals
Score model

Most likely scorelines.

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

#12:010.86%
#21:110.50%
#32:19.88%
#41:09.01%
#53:07.70%
Additional scorelines
3:17.00%
0:06.02%
2:24.49%
1:24.22%
4:04.09%
Team context

Strength and recent form.

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

Home

Manchester City

Elo1649.7
Overall attack1.90
Overall defense1.14
Home attack1.98
Home defense1.03
Form signal+0.698
Last 5 xGF / xGA1.76 / 1.07
Last 10 xGF / xGA1.84 / 1.15
Last 10 xGD+0.70
League statusSTABLE · from ENG1 2025/26
Away

Sunderland

Elo1507.8
Overall attack1.14
Overall defense1.44
Away attack1.03
Away defense1.65
Form signal+0.188
Last 5 xGF / xGA1.65 / 1.40
Last 10 xGF / xGA1.47 / 1.38
Last 10 xGD+0.09
League statusSTABLE · from ENG1 2025/26
Elo difference
+141.8

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 matches2Effective: 1.19
Average goals1.46Manchester City 1.46 · Sunderland 0.00
H2H 3+ goals48.77%Historical context
H2H BTTS0.00%Model BTTS: 53.79%
H2H 2+ goals48.77%
H2H 3+ goals48.77%
H2H 4+ goals0.00%
H2H BTTS0.00%
Goal distribution

Total goals profile.

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

06.02%
112.18%
223.35%
322.40%
417.00%
510.32%
65.22%
7+3.53%
0–1 goals18.19%Low total
2+ goals81.81%Over 1.5
3+ goals58.46%Over 2.5
4+ goals36.06%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
LeagueENG1
Loaded teams27
Loaded historical matches1560
Target season2026/27
Previous seasons in history4
Season window2022/23 → 2023/24 → 2024/25 → 2025/26 → 2026/27
League tierTier 1
Historical league matches1560
xG matches1560 / 1560
Effective xG matches797.37
Observed home xG1.60
Observed away xG1.31
Model home xG baseline1.60
Model away xG baseline1.31
Total league xG baseline2.91
Home-advantage weight1.000
Model configdata/models/ENG1.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 / A2.13 / 0.91
Relative strengths and form diagnostics

Manchester City

Home attack strength1.181
Home defense weakness0.835
Base lambda home1.93
Attack form xGF level1.793
Defense form xGA level (lower is better)1.094
Opponent-adjusted attack residual+0.283
Opponent-adjusted defense residual (higher is better)+0.309
Opponent-adjustment weight0.000
Model attack signal+0.338
Model defense signal+0.361
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD1.76 / 1.07 / +0.70
Last 10 xGF / xGA / xGD1.84 / 1.15 / +0.70

Sunderland

Away attack strength0.852
Away defense weakness1.022
Base lambda away0.93
Attack form xGF level1.583
Defense form xGA level (lower is better)1.395
Opponent-adjusted attack residual+0.116
Opponent-adjusted defense residual (higher is better)+0.044
Opponent-adjustment weight0.000
Model attack signal+0.128
Model defense signal+0.060
Opponent blend0.000
Form matches 5 / 105 / 10
Last 5 xGF / xGA / xGD1.65 / 1.40 / +0.24
Last 10 xGF / xGA / xGD1.47 / 1.38 / +0.09
Historical data coverage

Manchester City

Total matches156
Home / away matches78 / 78
xG matches156 / 156
xG home / away coverage78 / 78 · 78 / 78
Effective total31.95
Effective attack / defense31.95 / 31.95
Effective home matches16.01
Effective home attack / defense16.01 / 16.01

Sunderland

Total matches42
Home / away matches21 / 21
xG matches42 / 42
xG home / away coverage21 / 21 · 21 / 21
Effective total22.28
Effective attack / defense22.28 / 22.28
Effective away matches11.06
Effective away attack / defense11.06 / 11.06
Historical data coverage
63.66%

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 1540 historical matches.

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

Total goals log-loss vs baseline+0.33%
1X2 log-loss vs baseline+8.42%
BTTS Brier vs baseline+0.34%
Over 2.5 Brier vs baseline+1.35%
Full backtest metrics
Model
MAE total goals1.3233
Exact score log-loss2.9835
Total goals Brier0.8274
Total goals log-loss1.9007
1X2 Brier0.5851
1X2 log-loss0.9823
BTTS Brier0.2450
Over 1.5 Brier0.1570
Over 2.5 Brier0.2410
Over 3.5 Brier0.2228
League baseline
MAE total goals1.3154
Exact score log-loss3.1001
Total goals Brier0.8292
Total goals log-loss1.9070
1X2 Brier0.6488
1X2 log-loss1.0726
BTTS Brier0.2459
Over 1.5 Brier0.1572
Over 2.5 Brier0.2443
Over 3.5 Brier0.2253
Calibration diagnostics
Home win · ECE 2.59%
 0- 10%  n=14   avg=  8.3% actual=  7.1%
10- 20%  n=95   avg= 16.3% actual= 11.6%
20- 30%  n=246  avg= 25.8% actual= 22.4%
30- 40%  n=343  avg= 35.2% actual= 39.4%
40- 50%  n=322  avg= 44.8% actual= 44.7%
50- 60%  n=258  avg= 55.1% actual= 56.2%
60- 70%  n=164  avg= 64.5% actual= 68.3%
70- 80%  n=83   avg= 74.1% actual= 75.9%
80- 90%  n=15   avg= 84.1% actual= 93.3%
Draw · ECE 1.32%
 0- 10%  n=3    avg=  9.4% actual=  0.0%
10- 20%  n=139  avg= 17.0% actual= 14.4%
20- 30%  n=1257 avg= 25.9% actual= 25.6%
30- 40%  n=141  avg= 31.1% actual= 22.0%
Away win · ECE 3.45%
 0- 10%  n=82   avg=  7.6% actual=  7.3%
10- 20%  n=309  avg= 15.6% actual= 15.5%
20- 30%  n=391  avg= 25.0% actual= 21.0%
30- 40%  n=346  avg= 34.5% actual= 38.7%
40- 50%  n=235  avg= 44.3% actual= 41.7%
50- 60%  n=119  avg= 54.3% actual= 63.9%
60- 70%  n=43   avg= 64.5% actual= 74.4%
70- 80%  n=12   avg= 73.2% actual= 75.0%
80- 90%  n=3    avg= 81.8% actual= 66.7%
BTTS · ECE 2.58%
30- 40%  n=3    avg= 35.9% actual= 33.3%
40- 50%  n=202  avg= 47.4% actual= 49.0%
50- 60%  n=854  avg= 55.3% actual= 57.0%
60- 70%  n=461  avg= 63.5% actual= 59.2%
70- 80%  n=20   avg= 71.1% actual= 60.0%
Over 2.5 · ECE 2.57%
20- 30%  n=1    avg= 26.1% actual=  0.0%
30- 40%  n=32   avg= 37.7% actual= 43.8%
40- 50%  n=344  avg= 46.1% actual= 49.4%
50- 60%  n=654  avg= 55.1% actual= 57.2%
60- 70%  n=433  avg= 64.3% actual= 62.6%
70- 80%  n=75   avg= 72.9% actual= 66.7%
80- 90%  n=1    avg= 80.1% actual=100.0%
Walk-forward - latest periods
Period N Model 1X2 LL Baseline 1X2 LL Improvement
2025-08 30 0.9775 1.0463 +6.58%
2025-09 30 0.9920 1.0984 +9.68%
2025-10 30 0.9667 0.9993 +3.26%
2025-11 40 0.9613 1.0369 +7.29%
2025-12 56 0.9987 1.0989 +9.11%
2026-01 49 1.1387 1.1126 -2.34%
2026-02 42 1.0318 1.1382 +9.34%
2026-03 32 1.1246 1.0900 -3.17%
2026-04 30 1.0012 1.0588 +5.44%
2026-05 41 1.0345 1.0728 +3.57%
2026-08 20 0.9484 1.0473 +9.44%
2026-09 20 1.1195 1.1976 +6.53%

Football is data.

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

Back to Matches Follow on X