Expected goals
Home xG / Away xG
Bundesliga - 28321
Current lifecycle fixture
Kickoff
2026-09-12 00:00:00
VS

Intelligence overview
Highest 1X2 estimate 45%. Confidence is low, so the UI avoids a strong recommendation.
Expected goals
Home xG / Away xG
Model
analysis-v1
live-local
Publication
published
Public view hides drafts
Confidence
Low confidence
Cautious estimate
AI MATCH ANALYSIS
Model leans to a Hoffenheim win (45% probability) but assigns low confidence (43). Expected goals are high on both sides (2.0 v 1.9) producing a combined xG of 3.9; Over 1.5 is effectively certain, Over 2.5 likely and Both Teams To Score very probable.
The prediction favours a Hoffenheim win (45%) ahead of a draw (29%) or Stuttgart win (26%), but confidence is low. The market signal is that both sides should contribute goals: expectedHomeGoals 2.0 and expectedAwayGoals 1.9 produce a combined 3.9 xG and very high probabilities for goal markets.
The model cites Hoffenheim's stronger recent form trend as a driver of the home-lean. That input, combined with a stronger home win rate signal, nudges the primary outcome toward Hoffenheim despite a narrow gap in expected goals.
Hoffenheim's home output (reported average 2.1 goals per home match) and a stronger home win rate are primary home-side strengths. Stuttgart's away defensive profile — conceding 1.9 goals per away match — increases the probability of goals for both sides.
Combined expected goals are 3.9 (expectedHomeGoals 2.0, expectedAwayGoals 1.9). The model gives 100% probability to Over 1.5, 76% to Over 2.5 and 90% to Both Teams To Score — all signals point to an open, goal-rich fixture.
Over 1.5
100% probability — model treats scoring at least twice as a near-certainty given the combined xG.
Over 2.5
76% probability — a strong likelihood that the match will clear 2.5 goals, consistent with the 3.9 combined xG.
BTTS
90% probability — both sides expected to score; Stuttgart's 1.9 expected away goals and Hoffenheim's home scoring support this.
Expected goals
TSG Hoffenheim: 2
VfB Stuttgart: 1.9
TSG Hoffenheim
Home scoring projection
Model inputs record Hoffenheim at 2.1 average home goals — a meaningful attacking edge in expected-goals terms.
VfB Stuttgart
Away attacking contribution
Despite being the away side, Stuttgart carry an expected-away-goals figure (1.9) that keeps them firmly in the game and drives the BTTS signal.
Overall
High combined xG
A combined expected-goals value of 3.9 creates elevated probabilities across goal markets and increases outcome variance.
Low model confidence
The confidence score is 43 (labelled Low), indicating the model assigns limited certainty to the predicted outcome despite clear goal signals.
Narrow expected-goals gap
ExpectedHomeGoals 2.0 vs ExpectedAwayGoals 1.9 is a slim margin; a small variation in underlying events could flip the match outcome.
Limited recent-match sample usage
Provenance shows only one home and one away match were used in the feature set (homeMatchesUsed=1, awayMatchesUsed=1), increasing sensitivity to small-sample noise.
Known prediction weaknesses
The system lists draw prediction and confidence calibration as known limitations, which affects interpretation of the 29% draw probability and the overall forecast reliability.
Final Verdict
The model gives Hoffenheim the most likely single outcome (45%) while flagging a high-goals game (combined xG 3.9, Over 1.5 = 100%, Over 2.5 = 76%, BTTS = 90%). Low confidence and a very small xG margin (2.0 v 1.9) mean the forecast is fragile: Hoffenheim is the marginal favourite, but the contest is highly susceptible to variation and both teams are expected to score.
Confidence language: Low (confidence score 43). This remains an analytical view, not a guaranteed selection.
Analysis Engine V1 calculates the probabilities. The AI writer explains the verified inputs and does not alter numbers, add odds, or claim certainty.
Source datasets: live-local. Generated 2026-07-14T17:17:22.324Z.
Exact model percentages, never bookmaker odds.
Model-estimated probability, not odds.
Model-estimated probability, not odds.
Model-estimated probability, not odds.
Model-estimated probability, not odds.
Model-estimated probability, not odds.
Model-estimated probability, not odds.
A probability is an estimated chance from the local model context. It is not an outcome promise and is not bookmaker odds.
Market intelligence
A separate explanation layer for match markets. These signals do not change Analysis Engine V1 and are not bookmaker odds.
V1 expects 3.9 total goals. Local team samples average 3.49 total goals in matches involving these sides.
The winner market remains separated from goals markets, so a high goal signal does not automatically mean a strong home or away call.
Sportmonks returned corner statistics in the access audit. Per-team corner trends are not available for this fixture yet.
Sportmonks returned yellow cards, red cards and ball-possession statistics in the access audit. Match-specific trend import is pending.
Risk review
Short caution signals that explain why the analysis remains measured. These do not change the V1 prediction.
Draw tendency sample
22%
Combined draw share across both team samples.
V1 draw estimate shown for transparency.
Confidence caution
Cautious
Low-confidence analysis should avoid strong wording.
Manual publication remains required.
Historical sample context
68 matches
Current-season form will appear separately after Sportmonks current-season imports are expanded.
Longer-term profile from completed local datasets: 2025/2026. Current-season signals appear separately when Sportmonks match data is available.
TSG Hoffenheim form
PPG 1.79 - GF 65 - GA 52
VfB Stuttgart form
PPG 1.82 - GF 71 - GA 49
Home team signal
Points profile
1.79 PPG
18W 7D 9L sample
Goals for
1.91
65 scored across local sample
Goals against
1.53
52 conceded across local sample
Away team signal
Points profile
1.82 PPG
18W 8D 8L sample
Goals for
2.09
71 scored across local sample
Goals against
1.44
49 conceded across local sample
Match timeline
Goals, cards, VAR and substitutions appear only when verified Sportmonks event data exists locally.