2. Bundesliga · Germany · Regular Season - 3

SV Darmstadt 98–Hertha BSC

0–0

HT 0–0

Kick-off: Sunday, 24 August 2025 at 11:30
Status: Match Finished
Venue: Merck-Stadion am Bollenfalltor, Darmstadt

What the model said, and what happened

Ended level — we gave the draw 25%

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

Match statistics

Match statistics
SV Darmstadt 98		Hertha BSC
14	Shots	15
4	Shots on target	1
9	Shots inside the box	11
0	Goalkeeper saves	4
7	Corners	2
1	Offsides	1
60%	Possession	40%
466	Passes	313
397	Accurate passes

What we expected, and what happened

Expected goals before kick-off: SV Darmstadt 98 1.76 · Hertha BSC 1.23. On the pitch: 0-0.
Shots SV Darmstadt 98 14 · Hertha BSC 15; on target 4 and 1.
SV Darmstadt 98 kept the ball more (60%).

Referee

L. Erbst→

4.85

yellows per match

0.23

reds per match

matches of data

13 matches is a small sample — these averages are noisy and should not be read as a tendency.

Model prediction

Why this prediction?

The model puts the most likely outcome at 48.8%: “SV Darmstadt 98 to win”. Second comes “Hertha BSC to win” at 26.1%.
Behind that distribution are the expected goals: 1.78 for SV Darmstadt 98, 1.27 for Hertha BSC.
The highest double chance value is 74.9% (12 — any result other than a draw).
These values were computed from 942 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.

SV Darmstadt 98 to win48.8%

Draw25.1%

Hertha BSC to win26.1%

When the model has said 45–50% in the past, 1,541 of 3,251 predictions were correct (47.4%). Accuracy record →

12	Fouls	17

1	Yellow cards	1

0	Red cards	0

First half

Actual: 0–0

SV Darmstadt 98 lead at half-time43.0%

Level at half-time39.2%

Hertha BSC lead at half-time17.8%

First-half double chance

1X — SV Darmstadt 98 ahead or level82.2%

12 — not level at half-time60.8%

X2 — level or Hertha BSC ahead57.0%

These values are not a fraction of the full-match prediction; they come from a separate model trained on the first-half scores of 942 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

SV Darmstadt 98: at least 10Actual: 12
Hertha BSC: at least 12Actual: 17

Corners

SV Darmstadt 98: at least 4Actual: 7
Hertha BSC: at least 5Actual: 2

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.

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 SV Darmstadt 98 score1.76

Attack: SV Darmstadt 98 score close to the league average.

Opponent's defence: Hertha BSC's defence is close to the league average (0.94×), so it doesn't move the expectation much.

Result: These two effects give an expectation of 1.76 goals (including home advantage).

How many goals Hertha BSC score1.23

Attack: Hertha BSC score close to the league average.

Opponent's defence: SV Darmstadt 98's defence is close to the league average (0.94×), so it doesn't move the expectation much.

Result: These two effects give an expectation of 1.23 goals (including the away penalty).

Most likely scorelines

1–112.2%2–110.5%1–07.5%

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.

Week 3 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.