ITA1 · Serie A · Match Analysis

Juventus vs
Atalanta

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

60.30%

Juventus

Draw

24.17%

Away win

15.54%

Atalanta

Expected goals 1.94 – 0.90 2.83 total

BTTS 52.08% Both teams to score

Over 1.5 78.80% 2+ total goals

Over 2.5 53.87% 3+ total goals

Score model

Most likely scorelines.

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

#11:111.55%

#22:011.00%

#31:010.04%

#42:19.89%

#50:07.20%

Additional scorelines

3:07.10%

3:16.38%

1:24.60%

2:24.45%

0:13.95%

Team context

Strength and recent form.

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

Home

Juventus

Elo1589.1

Overall attack1.60

Overall defense0.45

Home attack1.59

Home defense0.18

Form signal+1.038

Last 5 xGF / xGA1.53 / 0.49

Last 10 xGF / xGA1.53 / 0.49

Last 10 xGD+1.04

League statusSTABLE · from ITA1 2025/26

Away

Atalanta

Elo1552.5

Overall attack0.87

Overall defense2.00

Away attack0.70

Away defense2.97

Form signal-1.001

Last 5 xGF / xGA0.95 / 1.95

Last 10 xGF / xGA0.95 / 1.95

Last 10 xGD-1.00

League statusSTABLE · from ITA1 2025/26

Elo difference

+36.6

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.

H2H matches8Effective: 2.37

Average goals2.15Juventus 0.98 · Atalanta 1.17

H2H 3+ goals25.15%Historical context

H2H BTTS45.07%Model BTTS: 52.08%

H2H 2+ goals63.67%

H2H 3+ goals25.15%

H2H 4+ goals25.15%

H2H BTTS45.07%

Goal distribution

Total goals profile.

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

07.20%

114.00%

224.93%

322.30%

415.80%

58.96%

64.23%

7+2.58%

0–1 goals21.20%Low total

2+ goals78.80%Over 1.5

3+ goals53.87%Over 2.5

4+ goals31.57%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

LeagueITA1

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 matches40 / 1560

Effective xG matches39.32

Observed home xG1.55

Observed away xG1.43

Model home xG baseline1.55

Model away xG baseline1.43

Total league xG baseline2.98

Home-advantage weight1.000

Model configdata/models/ITA1.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 / A1.94 / 0.90

Relative strengths and form diagnostics

Juventus

Home attack strength1.005

Home defense weakness0.759

Base lambda home1.79

Attack form xGF level1.533

Defense form xGA level (lower is better)0.495

Opponent-adjusted attack residual+0.002

Opponent-adjusted defense residual (higher is better)+0.955

Opponent-adjustment weight0.000

Model attack signal+0.043

Model defense signal+0.995

Opponent blend0.000

Form matches 5 / 104 / 4

Last 5 xGF / xGA / xGD1.53 / 0.49 / +1.04

Last 10 xGF / xGA / xGD1.53 / 0.49 / +1.04

Atalanta

Away attack strength0.918

Away defense weakness1.146

Base lambda away0.99

Attack form xGF level0.954

Defense form xGA level (lower is better)1.954

Opponent-adjusted attack residual-0.586

Opponent-adjusted defense residual (higher is better)-0.511

Opponent-adjustment weight0.000

Model attack signal-0.536

Model defense signal-0.464

Opponent blend0.000

Form matches 5 / 104 / 4

Last 5 xGF / xGA / xGD0.95 / 1.95 / -1.00

Last 10 xGF / xGA / xGD0.95 / 1.95 / -1.00

Historical data coverage

Juventus

Total matches156

Home / away matches78 / 78

xG matches4 / 156

xG home / away coverage2 / 78 · 2 / 78

Effective total3.80

Effective attack / defense3.80 / 3.80

Effective home matches1.90

Effective home attack / defense1.90 / 1.90

Atalanta

Total matches156

Home / away matches79 / 77

xG matches4 / 156

xG home / away coverage3 / 79 · 1 / 77

Effective total3.80

Effective attack / defense3.80 / 3.80

Effective away matches0.96

Effective away attack / defense0.96 / 0.96

Historical data coverage

3.61%

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+0.05%

1X2 log-loss vs baseline+1.81%

BTTS Brier vs baseline-0.07%

Over 2.5 Brier vs baseline+0.01%

Full backtest metrics

Model

MAE total goals1.2539

Exact score log-loss2.8802

Total goals Brier0.8149

Total goals log-loss1.8195

1X2 Brier0.6445

1X2 log-loss1.0666

BTTS Brier0.2523

Over 1.5 Brier0.1938

Over 2.5 Brier0.2495

Over 3.5 Brier0.1873

League baseline

MAE total goals1.2543

Exact score log-loss2.9055

Total goals Brier0.8149

Total goals log-loss1.8204

1X2 Brier0.6583

1X2 log-loss1.0863

BTTS Brier0.2522

Over 1.5 Brier0.1939

Over 2.5 Brier0.2495

Over 3.5 Brier0.1875

Calibration diagnostics

Home win · ECE 9.17%

10- 20%  n=1    avg= 18.3% actual=  0.0%
20- 30%  n=7    avg= 25.5% actual= 71.4%
30- 40%  n=432  avg= 38.4% actual= 21.3%
40- 50%  n=1097 avg= 42.3% actual= 48.1%
50- 60%  n=3    avg= 52.5% actual= 66.7%

Draw · ECE 1.78%

20- 30%  n=1533 avg= 29.0% actual= 27.3%
30- 40%  n=7    avg= 31.2% actual= 14.3%

Away win · ECE 13.48%

20- 30%  n=869  avg= 28.3% actual= 18.4%
30- 40%  n=662  avg= 31.6% actual= 49.8%
40- 50%  n=6    avg= 45.5% actual= 33.3%
50- 60%  n=3    avg= 53.6% actual= 66.7%

BTTS · ECE 4.90%

40- 50%  n=5    avg= 48.4% actual= 60.0%
50- 60%  n=1522 avg= 55.0% actual= 50.1%
60- 70%  n=13   avg= 63.0% actual= 61.5%

Over 2.5 · ECE 2.03%

30- 40%  n=3    avg= 39.5% actual= 33.3%
40- 50%  n=1382 avg= 49.3% actual= 47.3%
50- 60%  n=148  avg= 51.0% actual= 49.3%
60- 70%  n=7    avg= 63.0% actual= 57.1%

Walk-forward - latest periods

Period	N	Model 1X2 LL	Baseline 1X2 LL	Improvement
2025-08	20	1.0604	1.0893	+2.65%
2025-09	30	1.0695	1.0886	+1.75%
2025-10	40	1.0919	1.1084	+1.49%
2025-11	39	1.0768	1.0934	+1.52%
2025-12	37	1.0641	1.0757	+1.07%
2026-01	58	1.0680	1.1016	+3.05%
2026-02	40	1.0634	1.0959	+2.97%
2026-03	36	1.0330	1.0535	+1.94%
2026-04	40	1.0600	1.0887	+2.63%
2026-05	40	1.0895	1.1124	+2.06%
2026-08	20	1.0284	1.0765	+4.47%
2026-09	20	1.0778	1.0812	+0.31%

Football is data.

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

Back to Matches Follow on X

Juventus vsAtalanta

Match probabilities.

Most likely scorelines.

Strength and recent form.

Juventus

Atalanta

Historical matchup context.

Total goals profile.

How the model reached the estimate.

Juventus

Atalanta

Juventus

Atalanta

Historical model performance.

Home win · ECE 9.17%

Draw · ECE 1.78%

Away win · ECE 13.48%

BTTS · ECE 4.90%

Over 2.5 · ECE 2.03%

Football is data.

Juventus vs
Atalanta