Colombia vs Portugal
Group K · Saturday, June 27, 2026, 23:30 UTC · Miami (Miami Gardens)
The model's read
Portugal hold a narrow edge at 43%, with Colombia at 28% and 29% for the draw. Goals project around 1.4–1.9 in an open game (both teams to score 62%, over 2.5 64%). The biggest single factor is Overall strength, favouring Portugal. Confidence sits at 52/100 with moderate upset risk; the underdog has paths to a result.
Auto-updated every hour as ratings, odds and news change.
Match outcome
oracle-v1.0.0
Colombia win
27.9%
Draw
29.3%
Portugal win
42.8%
Expected goals
1.40 – 1.89
Scoreline cluster
1-2 / 0-1 / 1-1
top exact 1-2 · 9.3%
Confidence
52/100
Result lean
Portugal narrow edge
Score band
Open 1-1 / 2-1 type game
Goal environment
Open
If it opens up — high-scoring alternative
2-2 at 6.5% — most likely scoreline with 3+ goals total.
no exact score is dominant; BTTS 62% and Over 2.5 64% both elevated; top three scorelines within 2 pp
Risk & uncertainty
Upset risk
44/100
Data quality
88/100
Uncertainty band
37 – 65%
Most likely scorelines
Top 12 from a Dixon-Coles adjusted Poisson matrix.
Top 12 most likely scorelines. Heat is relative to the most likely outcome. Colombia vs Portugal.
Team comparison
Rating profile across the key dimensions.
Ensemble breakdown
Final probabilities blend the technical model with every available source layer. Persisted 2026-07-11 02:02:33 UTC.
Final (blended) home
27.9%
Final draw
29.3%
Final away
42.8%
Source weights applied
- technical38.5%
- learned16.1%
- market19.3%
- crowd7.5%
- external0.0%
- intel8.6%
- fundamental7.0%
- sentimentMomentum3.0%
Source presence
- technical1 signal
- learned1 signal
- market31 signals
- crowd1 signal
- externalnot used
- intel64 signals
- fundamental25 signals
Why this prediction
High-coverage prediction — most signal classes are present and aligned.
Technical
74/100
Fundamentals
82/100
Betting
71/100
Prediction market
66/100
Sentiment
0/100
Top positive drivers
- · technical signal favours away (17.4 pp above uniform)
- · market signal favours away (10.3 pp above uniform)
- · learned signal favours away (4.5 pp above uniform)
Top risk drivers
- · crowd signal is against away (-3.0 pp below uniform)
Missing: external prediction sites
Learned model
The learned model contributes to the public ensemble blend, alongside ratings, market signals and news intelligence. Performance is validated against an Elo baseline.
Colombia win
23.5%
Draw
38.7%
Portugal win
37.8%
Total goals (λ)
2.50
Model confidence
30/100
Logistic regression model — version wdl-v1, trained on 19k historical internationals.
Article intelligence
Recent news, injury alerts and sentiment extracted by the NLP layer.
Colombia
33 articles / 14d
Injury alerts
· Sanchez (out — ruled out)
Portugal
31 articles / 14d
Injury alerts
· Ronaldo (out — ruled out)
Goals markets
BTTS yes
62.2%
Over 1.5
82.3%
Over 2.5
63.9%
Over 3.5
41.8%
Under 2.5
36.1%
Market intelligence
Model probability
27.9%
Market probability
27.7%
Gap: +2.8 percentage points.
Market confidence: 98/100 across 31 bookmakers.
Odds shown for analysis only — CupCastLab does not place bets, list bookmakers, or recommend wagers.
Explanation
Why the model sees the match this way.
Model prediction: Portugal 51% to win, 30% for Colombia, 19% draw. Expected goals: Portugal 1.89 vs Colombia 1.40. Scoreline cluster: 1-2 / 0-1 / 1-1. Top exact 1-2 only 9.3%. Goal environment open (BTTS 62%, Over 2.5 64%). Open 1-1 / 2-1 type game. Primary factor: overall strength difference is the dominant driver. Confidence: 51/100. Moderate confidence; outcome is meaningfully uncertain.
Factor contributions
Risk factors
- No notable risk factors identified.
Uncertainty factors
- No major uncertainty flags.
Tactical read
No standout tactical mismatch — the stylistic edge is modest.
Upset risk
Moderate upset risk — the underdog has identifiable paths to a result.
Market divergence
Model and market are in close agreement.
These predictions are probabilistic and not guarantees. Not betting advice.