Round of 32 · Match 15
ColombiavsGhana
2026-07-04·20:00 local·Arrowhead Stadium · Kansas CityPredictions finalised
Match signals
Factors that favour each side, from statistical models to group stage form and match conditions. Longer bars = stronger advantage.
Colombia are dominant at 74% vs Ghana's 4%. Quality, form, and model estimates all point the same way. An upset here would be a major story.
📊What the Models Say
Rates teams by a single strength number updated after every match. Simpler but fast to react. It rates Colombia at 82% to win vs Ghana at 0%.
Simulates the goal-scoring process using attack and defence strength. The heaviest-weighted model. It rates Colombia at 70% to win vs Ghana at 8%.
Groups teams by confederation to share information. Helps for teams with fewer matches. It rates Colombia at 69% to win vs Ghana at 10%.
The published probability after calibration and adjustments. This is what the model says. It rates Colombia at 74% to win vs Ghana at 4%.
All 3 models agree: Colombia is favoured. When models agree, the signal is stronger.
⚽Tournament Form
Colombia collected 11 points (3W 2D 0L) vs Ghana's 4 (1W 1D 2L). A stronger tournament record.
Colombia averaged 1.0 goals per match vs Ghana's 0.5. More firepower coming in.
Colombia conceded just 0.2 goals/match vs Ghana's 0.75. Tighter at the back.
Colombia's goal difference of +4 is better than Ghana's -1. They outperformed opponents by more.
📈Momentum
Ghana's rating rose +42.4 during the tournament while Colombia's moved +10.0. The tournament has been kinder to Ghana.
Both squads' form ratings moved similarly during the tournament.
🏆Team Quality
Colombia is rated 1975 vs Ghana's 1503 (gap: 472). That's a very large gap in historical team strength.
The model expects Colombia to create 1.86 expected goals vs Ghana's 0.49. More and better chances projected.
Ghana's top 3 starters are harder to replace (avg VORP 0.36) than Colombia's (0.23). More star power in key positions.
Colombia's starters play together at club level more often (0.022 cohesion) than Ghana's (0.000). More shared understanding on the pitch.
🌍Match Conditions
Colombia traveled 4,340km vs Ghana's 9,748km. A shorter journey means less fatigue.
Colombia face a 0h timezone shift vs Ghana's 5h. Less jet lag disruption.
17 signals across 5 categories. Signal strength reflects how large the gap is between the two teams on each factor. Signals are descriptive, not prescriptive.
予測
Match-outcome probability
- Colombia win62.5%
- Draw27.1%
- Ghana win10.3%
A clash of identities: Colombia's pragmatic approach meets Ghana's counter-attacker style in a fixture the model gives to Colombia at 74%.
▸ゴールとスコアライン
Likeliest score 1–0 (17.3%) · xG 1.9 - 0.5
Expected goals
Mean of the Dixon-Coles joint goal distribution. Same fit that produces the most-likely-scoreline list below.
Most likely scorelines
- 1–017.3%
- 2–016.6%
- 3–010.3%
- 0–010.1%
- 1–19.2%
From the Dixon-Coles joint Poisson with the low-score correction. Scorelines are listed in probability order; this is a description of the model's distribution, not a recommendation.
Most likely half-time scorelines
- 0–031.3%
- 1–028.3%
- 2–013.4%
- 1–17.4%
- 0–17.1%
Same Dixon-Coles fit as the full-time list above, with rates halved to a 45-minute window and the low-score correction applied to that 1st-half block. The 0-0 row sits higher here than at full-time because fewer minutes have elapsed.
Goal totals
- More than 0.5 goals89.9%
- More than 1.5 goals68.5%
- More than 2.5 goals41.7%
- More than 3.5 goals21.0%
- More than 4.5 goals8.9%
- More than 5.5 goals3.3%
- Both teams score33.0%
Each row is the probability the match finishes with more than the listed number of goals. Both-teams-to-score is the probability each side scores at least once. All values are marginals of the Dixon-Coles joint goal grid that produces the scoreline list above — not market lines or any other operator construct.
Event-typed probabilities
- Colombia clean sheetOpposing team scores zero61.5%
- Ghana clean sheetOpposing team scores zero15.5%
Derived from the same Dixon-Coles joint distribution as the scoreline list. These are descriptive event probabilities — see CLAUDE.md §3/§4 (formerly COMPLIANCE.md §4.2.7) for the framing the project uses.
Win-margin probability
- Colombia by 4+8.6%
- Colombia by 3+21.4%
- Colombia by 2+43.6%
- Colombia by 1+70.2%
- Draw21.4%
- Ghana by 1+8.3%
- Ghana by 2+1.8%
- Ghana by 3+0.3%
- Ghana by 4+<0.1%
Each row is the probability the match ends with the listed margin or larger in that direction. Marginal of the Dixon-Coles joint goal grid; the “by 1+” rows plus the draw row sum to 1.
▸試合の展開
Over 2.5 goals 41.7% · BTTS 33.0%
Game state through the match
- Colombia ahead70.8%
- Level20.4%
- Ghana ahead8.9%
Probability of each game state at minutes 0, 15, 30, 45, 60, 75, 90 — derived from two independent thinned-Poisson processes with the Dixon-Coles per-team rates. The three lines always sum to 1 at each minute. The right column shows the state at the match's closing minute.
When the first goal arrives
- 0–1532.4%
- 15–3021.9%
- 30–4514.8%
- 45–6010.0%
- 60–756.8%
- 75–904.6%
- No goal9.6%
Probability the match's first goal arrives in each 15-minute window. Homogeneous Poisson with combined rate λ = λh + λa from the Dixon-Coles fit; the seven rows (six windows + no-goal tail) sum to 1.
Half-time / full-time grid
| HT ↓ / FT → | HColombia win | DDraw | AGhana win |
|---|---|---|---|
| HColombia ahead | 48.6% | 2.8% | 0.4% |
| DLevel | 20.5% | 15.0% | 3.7% |
| AGhana ahead | 1.7% | 2.7% | 4.7% |
Each cell is P(half-time result, full-time result). All nine cells sum to 1. Derived from a halved-λ Dixon-Coles fit for the first half plus an independent-Poisson second-half convolution.
Comeback probability
- Colombia trail at HT, avoid defeat at FT4.4%
- Ghana trail at HT, avoid defeat at FT3.2%
Joint probability — P(side trailing at half-time AND avoiding defeat at full-time). NOT conditional on trailing at HT. Derived from the same half-time / full-time decomposition that produces the HT/FT grid above; a tied first half is neither a home nor an away comeback opportunity.
PK shootout simulator
If the match ends level after extra time, the model estimates the shootout outcome from each team's Bayesian-smoothed conversion / save rate (Model #15). The bracket simulator uses the symmetric (averaged) ordering; the two what-if scenarios below show how the win probabilities shift when conditioning on which team kicks first.
- Colombia48.9%
- Ghana51.1%
- Colombia61.1%
- Ghana38.9%
- Colombia36.7%
- Ghana63.3%
First-kicker advantage
The first kicker's per-kick conversion rate is scaled by ×1.050 (about +5.0%), stacked on the Markov chain's structural asymmetry. Real World Cup shootouts use a coin toss for kicker order, so on average the order is 50/50 — the symmetric path above is the relevant number for a single fixture. The ordering-conditioned probabilities are a descriptive what-if scenario.
Literature: first kickers win ≈ 60% historically (Apesteguia & Palacios-Huerta, American Economic Review 2010; Vandebroek et al. 2016).
Per-team posteriors: Colombia conv 71.4%, save 22.9%; Ghana conv 72.5%, save 22.5%. Smoothed against the global prior with prior strength 20 — see /docs/methodology/.
▸チームと選手
Top scorer: Díaz (12.3%)
Match detail
Colombia
Model-rated key players: James Rodríguez (MF) — P(scores) 9.6%; Luis Díaz (FW) — P(scores) 12.3%; Jhon Córdoba (FW) — P(scores) 6.9%.
Colombia under Néstor Lorenzo play a pragmatic game with 53% possession. They apply moderate pressing intensity (PPDA 18.9).
Colombia play a pragmatic, results-oriented game that adapts shape to the opposition. Tactical flexibility is their strength. The risk is inconsistency — without a default identity, a poor result can cascade if the team struggles to find a Plan B.
Ghana
Model-rated key players: Jordan Ayew (FW) — P(scores) 10.5%; Antoine Semenyo (FW) — P(scores) 2.3%; Joseph Paintsil (FW) — P(scores) 2.1%.
Ghana under Carlos Queiroz play a counter attacker game, with just 43% possession — among the lowest in the field. Their likely shape is a 4-2-3-1, though they have also used 5-3-2. They apply moderate pressing intensity (PPDA 20.2) and move the ball forward quickly at 5.3 passes per attack. They are selective in their shooting (7.5 per 90) and favour high-quality chances (xG/shot 0.140, among the best in the field).
Ghana rely on defensive discipline and quick transitions — absorbing pressure and converting turnovers into attacking chances. Concentration and defensive organisation for full 90-minute stretches will determine whether the approach holds against top opposition. Managing minutes for Jordan Ayew across what could be seven matches will test the coaching staff's rotation planning.
Colombia historically converts 12.4% of xG from set-pieces, contributing 0.23 expected set-piece goals in this fixture. Ghana converts 5.2% from set-pieces (0.03 expected). Combined, the model expects 0.26 set-piece goals across the 90 minutes.
- P(Colombia scores set-piece goal) 20.6%
- P(Ghana scores set-piece goal) 2.5%
- P(set-piece goal in match) 22.6%
Colombia: James Rodríguez on corners (58 corners) (per fbref 2020 21) · Ghana: Salis Abdul Samed on free kicks (per fbref 2022 23)
If a penalty is awarded to Colombia, the model gives 71.4% conversion, 72.5% for Ghana. If this match goes to a shootout, the symmetric (coin-toss averaged) win probability is 48.9% Colombia / 51.1% Ghana.
Colombia primary PK: James Rodríguez (2/2 in 2013-14, per fbref 2020 21) · Ghana primary PK: Jordan Ayew (1/1 in 2017-18, per fbref 2022 23).
Derived from the model's per-fixture forecast joint and supporting reference data (predicted squads, set-piece xG share, PK posteriors, club minutes). See /docs/methodology/ for the full methodology.
Squad depth
Most irreplaceable starters
Colombia
- Luis DíazWingerCover: Jaminton Campaz · 0.630.31gap
- Cucho HernándezStrikerCover: Luis Suárez · 0.570.20gap
- Jhon AriasWingerCover: Jaminton Campaz · 0.630.17gap
Ghana
- Lawrence Ati-ZigiGoalkeeperCover: Joseph Anang · 0.210.41gap
- Thomas ParteyDefensive midfieldCover: Elisha Owusu · 0.270.37gap
- Gideon MensahFull-backCover: Marvin Senaya · 0.260.29gap
Gap = how far a side's rating at the position falls from the starter to his likely in-squad replacement (named under each name). Larger = harder to replace. Descriptive metric, does not feed the published probabilities. Methodology →
Match conditions
- AltitudeNear sea level229 m
- Avg temperatureFive-year mean over the tournament window25.8 °C
- Avg humidity69%
- Heat stressShade WBGT ~27.5 °CLow heat stress
- Pitch surfacenatural grass
Natural-grass NFL stadium; FIFA-standard hybrid pitch for the tournament.
Heat stress is a shade Wet-Bulb Globe Temperature proxy from the venue's climatology mean temperature and humidity; FIFA mandates cooling breaks at WBGT 32 °C. Evening kickoff (local time). These are long-window averages, not a match-day forecast, and they are not inputs to the forecast.
Top scorers · P(scores in this match)
- James RodríguezPKMF9.6%
- Luis DíazFW12.3%
- Jhon CórdobaFW6.9%
- Jordan AyewPKFW10.5%
- Antoine SemenyoFW2.3%
- Joseph PaintsilFW2.1%
Per-player scoring rate from Model #5 (`p_score_per_match`). Reflects each player's npxG/90, expected minutes, team xG share, and the average opposing-team defence. See /docs/methodology/.
Recent match form
Last match player ratings
Colombia
vs Portugal · avg 6.6
Ghana
vs Croatia · avg —
Player scores from official highlight analysis of each team's most recent match. Observational, not a model input. Methodology →
Video analysis: player performance
Per-player ratings and event breakdowns from official highlights analysis. Tap a player to see their full match timeline.
8Luis SuarezShowcased excellent skill and delivered a precise assist for the match-winning goal, demonstrating his creative influence.
Showcased excellent skill and delivered a precise assist for the match-winning goal, demonstrating his creative influence.
7Luis DiazA dynamic attacking presence who consistently created chances but was let down by his finishing on two key opportunities.
A dynamic attacking presence who consistently created chances but was let down by his finishing on two key opportunities.
7Mejia45'–45'Created a significant scoring opportunity with a well-struck shot that required a top-class save from the opposition goalkeeper.
1shots1on target▼
Created a significant scoring opportunity with a well-struck shot that required a top-class save from the opposition goalkeeper.
Match timeline
6Quintero83'–83'Contributed an offensive effort late in the game with a powerful long-range strike that ultimately missed the target.
1shots▼
Contributed an offensive effort late in the game with a powerful long-range strike that ultimately missed the target.
Match timeline
9Ati-Zigi45'–57'Ghana's standout performer, making multiple heroic saves that kept the scoreline respectable and prevented a larger defeat.
2saves▼
Ghana's standout performer, making multiple heroic saves that kept the scoreline respectable and prevented a larger defeat.
Match timeline
5ParteyHad an early attempt on goal but his overall impact on the match was limited to this single offensive action.
1shots▼
Had an early attempt on goal but his overall impact on the match was limited to this single offensive action.
Match timeline
5Semenyo52'–52'Showed individual initiative by driving into the box but failed to connect with a teammate for a meaningful chance.
▼
Showed individual initiative by driving into the box but failed to connect with a teammate for a meaningful chance.
Match timeline
Match observations
- Colombia secured a narrow 1-0 victory over Ghana in a hard-fought Round of 32 encounter.
- The match was characterized by Colombia's attacking prowess and Ghana's resilient defending, particularly from their goalkeeper.
- Colombia created numerous opportunities, especially on the counter-attack, while Ghana struggled to convert their limited chances.
▸モデルの内部
Model-by-model comparison
Colombia vs Ghana
| Model | Weight | Home | Draw | Away |
|---|---|---|---|---|
| EloRating-based strength estimate | 32% | 81.6% | 18.4% | 0.0% |
| Dixon-ColesGoal-process model with low-score correction | 63% | 70.3% | 21.3% | 8.4% |
| Hierarchical PoissonBayesian model with confederation pooling | 6% | 68.6% | 21.9% | 9.5% |
| Bayesian stackingLearned-weight combination | — | 82.0% | 18.0% | 0.0% |
| Ensemble (published)Uniform average + isotonic calibration | — | 73.6% | 22.3% | 4.1% |
How each model works
- Elo
- Each team carries a single strength rating updated after every match by a margin-aware K-factor. Match probabilities come from the logistic function of the rating gap. Elo is fast-adapting but coarse — it sees only who won and by how much, not how the goals were scored.
- Dixon-Coles
- A Poisson regression on team-level attack and defence parameters, fitted via maximum likelihood with an exponential time-decay weighting. The Dixon-Coles correction adjusts the four low-score cells (0-0, 1-0, 0-1, 1-1) where independent Poisson underestimates dependence. Produces full scoreline distributions, not just H/D/A.
- Hierarchical Poisson
- A Bayesian Poisson model fitted via MCMC (PyMC) with hierarchical priors that pool attack and defence parameters within confederations. Shrinks small-sample teams toward their confederation mean — helpful for nations with few recent competitive fixtures. Slower to fit but better-calibrated on the tails.
- Bayesian stacking
- Optimises simplex weights (w_elo, w_dc, w_hp) to maximise the leave-one-out log-score across a walk-forward backtest (Yao et al. 2018). The result is a weighted average of the three component models' probabilities, then isotonic-calibrated. Adds no extra features — just learns which component to trust more from historical accuracy.
- Ensemble (published)
- Equal-weight average of all three component models, followed by per-class isotonic regression calibration fitted on 24 months of walk-forward out-of-fold predictions. This is the probability published on the site. The uniform mean is deliberately simple — it avoids overfitting to the stacking weights' training window.
Three independent component models feed two combination strategies. The uniform ensemble is the published probability; Bayesian stacking uses learned weights. Amber bars flag >5pp divergence from the published number. Full methodology
Latest news & match context
No recent headlines for Colombia or Ghana.
- Stage:
- Round of 32 · Match 15
- Date:
- 4 Jul
- Venue:
- Arrowhead Stadium, Kansas City
Ranked by likely importance. None of these feed the forecast: the probabilities rest on team strength, venue conditions and the style matchup.
- 1.Elimination stakes: A one-off elimination tie. Motivation, risk appetite and game management under tournament pressure are not model inputs; the forecast rests on team strength and the style matchup.
Colombia and Ghana both come in at close to full strength, so the forecast rests on baseline team strength rather than late team-news swings.
Availability from the predicted squads and injury feed; forecast adjustments from the model's own decomposition. See /docs/methodology/.
Standard Pass
この試合は無料プレビューです
この試合のモデル予測をすべて無料でご覧いただいています。確率、期待ゴール数、スコアライン分布、選手別得点確率を全 104 試合で解除するには、大会終了まで有効な Standard Pass をどうぞ。
Every forecast graded against the real result, scored on 987 matches since 2014. See the scorecard.
24h money-back, no questions asked·No subscription, no auto-renewal·Access through 31 Dec 2026. See refund policy.