betaider.com

Paderborn v Hoffenheim — Prediction, Odds & Stats

Sunday 20 September 2026 · GER-Bundesliga · 2627

Bundesliga xG Prediction generated

AI prediction

ai-blend v1.0 daily
Paderborn win
35.8%
Draw
25.6%
Hoffenheim win
38.6%

Raw model output; no calibration record for this fixture's bands yet.

Top 5 scorelines

  1. 1-1 12.1%
  2. 0-1 9.1%
  3. 1-0 8.7%
  4. 1-2 8.5%
  5. 2-1 8.1%

Goals

Over 2.551.4% Under 2.548.6%
BTTS yes55.5% BTTS no44.5%
Paderborn 1+73.7% Paderborn 2+38.6%
Hoffenheim 1+75.3% Hoffenheim 2+40.7%

Expected goals 1.34 – 1.40. Every market above is read off one scoreline distribution.

Footing

AI confidence
79/100
Data quality
65/100
Model agreement
98%
★ Best pick
Nothing on a measured band prices above 1.18 here.
★ Most likely to land
Nothing on a measured band prices above 1.18 here.

Positive factors

  • Hoffenheim carry the stronger rating, 1539 Elo against 1485.
  • Hoffenheim have created 1.79 xG a match over their last five while Paderborn have allowed 1.36.
  • Away from home Hoffenheim average 1.61 xG a match.

Risk factors

  • Paderborn have only 2 matches on record.
Why the model thinks this

The price

Hoffenheim have an estimated 38.6% win probability, against 35.8% for Paderborn and 25.6% for the draw. Expected goals from the ensemble are 1.33 for Paderborn and 1.40 for Hoffenheim.

Why Paderborn

Paderborn have created 0.71 xG a match over their last five while Hoffenheim have allowed 1.90. At home Paderborn average 0.73 xG a match. Their last eleven was closer to full strength: Hoffenheim were missing 1.08 expected goal involvements a match against 0.16.

Why the draw is live

The draw sits at 25.6%. The sides are closely matched on expected goals, 1.33 to 1.40. Draws run at 25% in this competition.

Why Hoffenheim can win

Hoffenheim carry the stronger rating, 1539 Elo against 1485. Hoffenheim have created 1.79 xG a match over their last five while Paderborn have allowed 1.36. Away from home Hoffenheim average 1.61 xG a match.

Key players

Paderborn's leading contributors by expected goal involvements a match: Marvin Pieringer (0.36), Laurin Curda (0.22), Rayan Philippe (0.20). Hoffenheim's leading contributors by expected goal involvements a match: Tim Lemperle (0.40), Andrej Kramaric (0.39), Fisnik Asllani (0.36).

Availability

2 of Hoffenheim's top three contributors did not start their last match. 27% of Hoffenheim's last eleven are new to the club this window.

The matchup, as far as the data reaches

Paderborn: 54% possession, 12.0 shots a match, 19.0 faced, 0.11 xG a match from set pieces. Hoffenheim: 59% possession, 16.4 shots a match, 14.5 faced, 0.32 xG a match from set pieces.

Inputs last refreshed: matches 2026-09-06 07:42 · team_stats 2026-09-06 06:08 · availability 2026-09-06 07:53 · prediction 2026-09-05 18:39 ·

Hoffenheim are the model's most likely outcome at 38.6%. The likeliest scoreline is 1-1 at 12.1%. Confidence 79/100, data quality 65/100. These are probabilities, not certainties: the less likely outcome happens as often as its number says.

Written from the numbers the model saw, not by a language model; nothing here is a statistic the snapshot does not hold. How predictions work.

Was this pick made in advance?
A model whose name ends -oos is out of sample: it was fitted only on matches played before this one, so its pick is a genuine forecast rather than hindsight. Anything without that suffix was fitted on all available data.

What the chances say

Hoffenheim are finishing below their chances — 2.9 goals fewer than expected across 10 matches, despite creating the openings. They are also conceding sharply more than the chances against them merit — 5.0 goals above expected, which tends to correct.

LLDWWDWLLL last 10 scored 15 from 17.9 xG conceded 24 from 19.0 xG

Finishing swings far more than chance creation, so a gap this size usually narrows. Over ten matches it is suggestive, not settled — a genuinely elite finisher beats expected goals for years.

What the model said

ModelHome / Draw / Away Expected goalsLikeliest score O2.5BTTS
ai-blend 1.34–1.40 0% 0% 0%
dc-xg 1.17–1.24 1-1 13% 43% 49%

A model whose name ends -oos was produced by the walk-forward backtest: it was fitted only on matches played before this one, so the pick is genuinely out of sample.

betaider.com

Sport

Football sections

Preferences

Appearance
Aider Reading the Football model · online
Open the Radar
Bet slip
Open full page
to move to open esc to close See all results

On this page

Match

What this page is for

One fixture in full. The model's probability for every market it prices, the prices stored against them, the teams expected to feature, and for a match already played, the shot map and the xG timeline.

How to read the shot map

Every shot is placed where it was taken and sized by its chance of being scored. A cluster of small marks from distance and a clean sheet is a side that was busy without ever threatening; two big marks and a defeat is a side that had the better of it and lost anyway. Both happen constantly, and both are invisible in the score.

How to read the xG timeline

The steps are chances as they arrived, so the shape shows who was on top and when. A flat line that jumps once near the end is a smash and grab.

Things to watch

The stored prediction is the one made before the match, kept deliberately so it can be judged afterwards. It is not re-fitted with hindsight.

Press esc to close Read the full guide