UEFA Champions League · Knockout Round Play-offs
HT 0–0
The match was decided in extra time. The score covers more than 90 minutes, so it is not used to train the model.
Share on XToo close to call — only 4.3% between the top two
This verdict goes into the public record unchanged; we do not filter out the ones we get wrong. The model's track record
| PSV Eindhoven | Juventus | |
|---|---|---|
| 25 | Shots | 15 |
| 10 | Shots on target | 4 |
| 15 | Shots inside the box | 11 |
| 3 | Goalkeeper saves | 7 |
| 6 | Corners | 5 |
| 1 | Offsides | 1 |
| 59% | Possession | 41% |
| 663 | Passes | 449 |
| 552 | Accurate passes |
4.09
yellows per match
0.09
reds per match
57
matches of data
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.
When the model has said 40–45% in the past, 2,356 of 5,298 predictions were correct (44.5%). Accuracy record →
| 345 |
| 14 | Fouls | 20 |
|---|
| 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.
When the model has said 55–60% in the past, 3,524 of 6,225 predictions were correct (56.6%). Accuracy record →
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 (23.6%).
The 3+ goals prediction is not published for this match.
The model gives a probability below the baseline (55.3%). In backtesting the model's edge in the "fewer goals" direction could not be confirmed; we don't publish an unconfirmed prediction.
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.
Attack: PSV Eindhoven score 75% more than the league's average team — one of the sharpest attacks in the league.
Opponent's defence: Juventus concede 27% fewer than the league average, which pulls the expectation down.
Result: A strong attack meets a strong defence. The two largely cancel and the expectation drops to 1.55 goals — markedly lower than the attack alone would promise.
Attack: Juventus score above the league average (17% more).
Opponent's defence: PSV Eindhoven concede 28% fewer than the league average, which pulls the expectation down.
Result: These two effects give an expectation of 1.45 goals (including the away penalty).
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 1824 matches played in this league before kick-off; the team with fewer has 91 matches. No data from after the match was used. The model's track record is published unfiltered.