Bundesliga · Germany · Regular Season - 2

VfB Stuttgart–1. FC Köln

4–1

HT 1–0

Kick-off: Friday, 4 September 2026 at 18:30
Status: Match Finished

What the model said, and what happened

Prediction correct

This verdict goes into the public record unchanged; we do not filter out the ones we get wrong. The model's track record

Goals and red cards

39'VfB StuttgartB. El Khannouss (assist: J. Vagnoman)
60'VfB StuttgartG. Prömel (assist: M. Mittelstädt)
75'VfB StuttgartE. Demirović (assist: Finn Jeltsch)
81'1. FC KölnM. Bülter
90'VfB StuttgartJ. Vagnoman

Match statistics

Match statistics
VfB Stuttgart		1. FC Köln
22	Shots	18
8	Shots on target	5
15	Shots inside the box	14
3	Goalkeeper saves	4
10	Corners	8
1	Offsides	0
58%	Possession	42%
526	Passes	378
450	Accurate passes

What we expected, and what happened

Expected goals before kick-off: VfB Stuttgart 2.29 · 1. FC Köln 1.24. On the pitch: 4-1.
Shots VfB Stuttgart 22 · 1. FC Köln 18; on target 8 and 5.
VfB Stuttgart kept the ball more (58%).

Unavailable players

VfB Stuttgart

D. Seimenout · Thigh Injury
D. Zagadouout · Muscle Injury
J. Arevaloout · Back Injury
J. Diehlout · Muscle Injury
L. Jaquezout · Muscle Injury
L. Sauerout · Muscle Injury
N. Narteyout · injury
T. Tomasout · Muscle Injury
C. Fuhrichdoubtful · Muscle Injury
L. Assignondoubtful · Shoulder Injury

1. FC Köln

L. Waldschmidtout · Muscle Injury
S. El Malaout · illness
S. Sebulonsenout · Muscle Injury
T. Dallinga

Referee

C. Dingert→

4.41

yellows per match

0.14

reds per match

matches of data

Model prediction

Why this prediction?

The model puts the most likely outcome at 65.4%: “VfB Stuttgart to win”. Second comes “a draw” at 19.2%.
Behind that distribution are the expected goals: 2.43 for VfB Stuttgart, 1.18 for 1. FC Köln.
The highest double chance value is 84.6% (1X — VfB Stuttgart win or draw).
These values were computed from 1,233 past matches.

This is a prediction, not a guarantee; a probability is not a certainty.

These sentences are built by a fixed template; every number in them comes straight from the model's computation, none invented while the text was written.

VfB Stuttgart to win65.4%

Draw19.2%

1. FC Köln to win15.4%

When the model has said 65–70% in the past, 675 of 977 predictions were correct (69.1%). Accuracy record →

5	Fouls	6

1	Yellow cards	3

0	Red cards	0

The measurements our data provider sent for this match. A row that was not measured shows “—”; writing 0 into an empty field would claim we measured it and found none.

T. Hubersout · Knee Injury

Provider data — may change until the line-ups are announced. Last updated: Wednesday, 16 September 2026 at 15:11.

When the model has said 65–70% in the past, 575 of 859 predictions were correct (66.9%). Accuracy record →

Double chance

1X — VfB Stuttgart win or draw84.6%

12 — any result other than a draw80.8%

X2 — draw or 1. FC Köln win34.6%

These three values add up to 200%, not 100% — and that is not a mistake. The options are not mutually exclusive; every outcome is counted in two of them. For the same reason 1X plus X2 exceeds 100% by exactly the probability of a draw (19.2%).

First half

Actual: 1–0

VfB Stuttgart lead at half-time57.0%

Level at half-time32.6%

1. FC Köln lead at half-time10.4%

First-half double chance

1X — VfB Stuttgart ahead or level89.6%

12 — not level at half-time67.4%

X2 — level or 1. FC Köln ahead43.0%

These values are not a fraction of the full-match prediction; they come from a separate model trained on the first-half scores of 1233 matches. Its edge over the base rate is markedly smaller than the full-match model's — the measured figure is on the accuracy record. Read them more cautiously. First-half goal markets are not published because they failed to beat the base rate.

Expected fouls and corners

Fouls

VfB Stuttgart: at least 9Actual: 5
1. FC Köln: at least 9Actual: 6

Corners

VfB Stuttgart: at least 6Actual: 10
1. FC Köln: at least 3Actual: 8

These figures are set to hold in at least 60% of matches; in the rest the count comes in below them. No upper bound is stated — we make no "at most" claim. Yellow cards were measured and are not published: there our model did not beat the historical average.

Goals market

3+ goals71.4%

When the model has said 70–75% in the past, 405 of 553 predictions were correct (73.2%). Accuracy record →

The league's historical "3+ goals" rate is 61.7%. For this match the model gives a value above that baseline — and in backtesting the model's edge was confirmed only in this direction.

What these probabilities rest on

Expected goals comes out of a team's attack weighed against its opponent's defence. A strong attack is damped when it meets a strong defence — which is why comparing the ratings on their own is misleading.

How many goals VfB Stuttgart score2.29

Attack: VfB Stuttgart score above the league average (21% more).

Opponent's defence: 1. FC Köln's defence is close to the league average (1.08×), so it doesn't move the expectation much.

Result: These two effects give an expectation of 2.29 goals (including home advantage).

How many goals 1. FC Köln score1.24

Attack: 1. FC Köln score close to the league average.

Opponent's defence: VfB Stuttgart's defence is close to the league average (0.95×), so it doesn't move the expectation much.

Result: These two effects give an expectation of 1.24 goals (including the away penalty).

Most likely scorelines

2–110.4%1–18.5%3–18.4%

A single scoreline is always less likely than an outcome: “home win” is the sum of 1-0, 2-0, 2-1 and dozens more. So the most likely single score can be a draw while the most likely outcome is a home win; the two do not contradict each other.

Ratings were computed from 1233 matches played in this league before kick-off; the team with fewer has 103 matches. No data from after the match was used. The model's track record is published unfiltered.

Week 2 of the season. This prediction was computed from previous seasons. Summer transfers, budget changes and squad rebuilds aren't in the ratings yet — the model can only see that a team has been rebuilt once new results come in.

We measured this: the bias is only pronounced in the opening week. In this week the model's overall accuracy does not separate from the rest of the season — that is, we found no measurable flaw. The one tendency across all opening weeks is that home wins are called slightly too often (said 43.0%, got 41.9%; n=583).

This sample is small and not statistically established, which is why we do not correct the model for it. The correction we tried (pulling probabilities toward the league average) didn't win on holdout, so it wasn't added. Read opening-week predictions with a little more caution.