Expected goals
Home xG / Away xG
Premier League - 28083
Current lifecycle fixture
Kickoff
2026-08-29 16:30:00
VS

Intelligence overview
Highest 1X2 estimate 39%. 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 gives Tottenham a slim edge (39% home-win probability) in a fixture where scoring is likely: 80% for over 1.5 goals, 70% chance both teams score. Expected goals are nearly level (Tottenham 1.2, Newcastle 1.3). Confidence is low and the underlying sample is extremely small, so statistical signals should be treated as indicative rather than definitive.
The model classifies the match as a home-lean but without a clear favourite: home win probability is 39%, away 31% and draw 30%. Expected goals are marginally in Newcastle's favour (1.3 v 1.2), while goal-related markets (over 1.5 and BTTS) show stronger support. Overall confidence is low (34) and the result distribution is compact, meaning small data changes could alter the ranking.
The input lists a stronger recent-form trend for Tottenham as a primary reason, but the model used only one home match and one away match for each side. The limited sample amplifies short-term variance: any single result would heavily influence the model.
Although Tottenham are the home side, expected goals slightly favour Newcastle (1.3 away v 1.2 home). The input explicitly notes Tottenham's goal difference across the sample is -9, indicating their recent goal outcomes in the provided window are poorer despite the home designation.
The model indicates an 80% chance of over 1.5 goals, 43% for over 2.5, and 70% for both teams to score. Expected goals are balanced, which supports a view of multiple scoring events rather than a single-sided shutout.
Over 1.5
80% probability makes over 1.5 the strongest market signal in the data—expected goals combined (2.5) are consistent with a game that usually clears 1–2 goals.
Over 2.5
At 43% the over 2.5 market is marginal; the expected total goals (~2.5) sit close to the cusp, producing an outcome that could swing either side.
BTTS
70% BTTS probability is a clear indicator both sides show statistical support to score in the sample.
Expected goals
Tottenham Hotspur: 1.2
Newcastle United: 1.3
Tottenham Hotspur
Slight model preference
The model assigns the highest single probability to a Tottenham win (39%), reflecting a narrow statistical tilt in their favour.
Both
Strong goal probabilities
High probabilities for over 1.5 goals (80%) and BTTS (70%) indicate a robust expectation of scoring from both sides in the available data.
Very small sample size
Only one home match and one away match were used for each side; this creates high variance and means single-match noise can dominate signals.
Low model confidence
Confidence score is 34 (labelled Low). The prediction distribution is compact and the highest probability is only 39%, so outcomes are highly uncertain.
Known model weaknesses
Draw probability calibration is a documented V1 weakness and the provenance notes several limitations including seasonal variability and weak confidence calibration.
Final Verdict
The model assigns a narrow home advantage (39% home-win) while also signalling a strong likelihood of goals (80% over 1.5, 70% BTTS). Expected goals are balanced (1.2 v 1.3) and Tottenham's sample goal difference is negative, which complicates a straightforward home-advantage reading. Given the low confidence score (34) and the extremely small sample used, treat the outputs as indicative tendencies rather than firm predictions.
Confidence language: Low. 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 2026-07-14T11:20:09.564Z.
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 2.5 total goals. Local team samples average 2.8 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
24%
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
76 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.
Tottenham Hotspur form
PPG 1.08 - GF 48 - GA 57
Newcastle United form
PPG 1.29 - GF 53 - GA 55
Home team signal
Points profile
1.08 PPG
10W 11D 17L sample
Goals for
1.26
48 scored across local sample
Goals against
1.5
57 conceded across local sample
Away team signal
Points profile
1.29 PPG
14W 7D 17L sample
Goals for
1.39
53 scored across local sample
Goals against
1.45
55 conceded across local sample
Match timeline
Goals, cards, VAR and substitutions appear only when verified Sportmonks event data exists locally.