Group H · Matchday 3
Cape VerdevsSaudi Arabia
2026-06-26·19:00 localPredictions finalised
The forecast
Match-outcome probability
- Cape Verde win30.3%
- Draw33.2%
- Saudi Arabia win36.5%
The model projects one of the most closely-contested fixtures of the round — Cape Verde and Saudi Arabia are separated by fine margins across every outcome.
Why the model says this
Favoring Cape Verde
- ·Cape Verde has demonstrated greater stability in recent results, recording only 1 loss in their last 6 matches (1 win, 4 draws), compared to Saudi Arabia's 4 losses over the same period.
- ·Over their last six matches, Cape Verde holds a positive goal difference of +1 (10 goals scored, 9 conceded), contrasting with Saudi Arabia's negative goal difference of -5 (6 goals scored, 11 conceded).
Favoring Saudi Arabia
- ·Saudi Arabia is ranked 60th by FIFA, eight places higher than Cape Verde, who are ranked 68th.
- ·The model projects Saudi Arabia to generate more expected goals (0.96 xG) in this fixture compared to Cape Verde (0.83 xG).
- ·Key sub-models, including ELO (41.7% vs 36.3%), DC (36.0% vs 29.3%), and HP (34.1% vs 31.2%), consistently assign a higher win probability to Saudi Arabia.
What the model can't fully price
- ·One projected starter across both squads is carrying a fitness doubt. The model's current lineup channel does not account for this, meaning the impact of this potential absence is not factored into the probabilities.
- ·The 'Group H · Matchday 3' context implies this is a group stage match, where qualification scenarios or dead rubber status could influence team approach, which is not explicitly modeled.
- ·The venue for the match is not specified, meaning any specific conditions (e.g., altitude, pitch quality) that could influence performance are not factored into the probabilities.
Form check
Cape Verde
SteadyCape Verde has shown resilience recently, with only one loss in their last six matches. They have drawn four times, including two 1-1 results and a goalless draw, alongside a 3-0 victory. Their most recent loss was a 2-4 defeat.
1 loss in their last 6 matches
Saudi Arabia
DecliningSaudi Arabia's recent form has been challenging, with four losses in their last six fixtures. They secured two wins but suffered significant defeats, including a 0-4 loss and a 1-2 defeat in their most recent outing.
4 losses in their last 6 matches
Analysis
How it plays out
Cape Verde press high and force the tempo. Saudi Arabia's balanced setup needs to absorb that pressure early and find the right moments to play forward.
What decides it
Cape Verde press high (PPDA 17.2). If the press doesn't win the ball early, the space behind their back line becomes exposed. The scoring threat is evenly split: Nuno da Costa (6.6%) and Abdullah Al-Hamdan (5.3%).
Off the pitch
Bubista (6 years in charge of Cape Verde) vs Georgios Donis (0 years). That tenure gap shows up in squad familiarity and set-piece coordination.
The angle
A Group H fixture where the result matters more for the standings than the headlines.
▸Goals & scorelines
Likeliest score 0–0 (19.3%) · xG 0.9 - 0.8
Expected goals
Mean of the Dixon-Coles joint goal distribution. Same fit that produces the most-likely-scoreline list below.
Most likely scorelines
- 0–019.3%
- 1–014.9%
- 0–114.6%
- 1–114.0%
- 2–06.7%
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
- 0–043.4%
- 1–017.9%
- 0–117.5%
- 1–18.1%
- 2–03.9%
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 goals80.7%
- More than 1.5 goals51.1%
- More than 2.5 goals24.0%
- More than 3.5 goals9.2%
- More than 4.5 goals2.9%
- More than 5.5 goals0.8%
- Both teams score33.3%
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
- Cape Verde clean sheetOpposing team scores zero43.4%
- Saudi Arabia clean sheetOpposing team scores zero42.6%
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
- Cape Verde by 4+0.6%
- Cape Verde by 3+2.8%
- Cape Verde by 2+11.3%
- Cape Verde by 1+32.6%
- Draw35.8%
- Saudi Arabia by 1+31.6%
- Saudi Arabia by 2+10.8%
- Saudi Arabia by 3+2.7%
- Saudi Arabia by 4+0.5%
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.
▸How the match unfolds
Over 2.5 goals 24.0% · BTTS 33.3%
Game state through the match
- Cape Verde ahead33.4%
- Level34.2%
- Saudi Arabia ahead32.4%
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
- 0–1524.5%
- 15–3018.5%
- 30–4514.0%
- 45–6010.5%
- 60–758.0%
- 75–906.0%
- No goal18.5%
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 → | HCape Verde win | DDraw | ASaudi Arabia win |
|---|---|---|---|
| HCape Verde ahead | 19.4% | 4.0% | 0.9% |
| DLevel | 12.9% | 26.5% | 12.6% |
| ASaudi Arabia ahead | 0.9% | 4.0% | 18.8% |
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
- Cape Verde trail at HT, avoid defeat at FT5.0%
- Saudi Arabia trail at HT, avoid defeat at FT4.9%
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.
Cards
- Expected yellow cardsMean of the Poisson on total yellow cards.3.45
- Total yellows over 2.567.0%
- Total yellows over 3.545.3%
- Total yellows over 4.526.5%
- Any red cardP(at least one red card in the match).9.5%
Referee not yet assigned. Using the 2026 pool-mean per-match rate as a placeholder; the model picks up the referee's personal rate once the assignment is published. Total yellow cards modelled as a Poisson with mean equal to two team baselines plus the referee's deviation from the pool mean. Reds are modelled the same way, independently. See /docs/methodology/.
▸Teams & players
Top scorer: Livramento (8.0%)
Match detail
Cape Verde
Model-rated key players: Nuno da Costa (FW) — P(scores) 6.6%; Dailon Livramento (FW) — P(scores) 8.0%; Ryan Mendes (FW) — P(scores) 8.0%.
Cape Verde under Bubista play a high press game with 53% possession. They apply moderate pressing intensity (PPDA 17.2) and move the ball forward quickly at 5.7 passes per attack. They generate a high volume of shots (13.2 per 90).
Cape Verde need their high press to force turnovers in dangerous areas — if opponents can play through the press, the space left behind is vulnerable. Physical conditioning and squad rotation will be critical to sustain pressing intensity across a long tournament.
Saudi Arabia
Model-rated key players: Abdullah Al-Hamdan (FW) — P(scores) 5.3%; Firas Al-Buraikan (FW) — P(scores) 5.3%; Saleh Al-Shehri (FW) — P(scores) 5.3%.
Saudi Arabia under Georgios Donis play a balanced game with 52% possession. Their likely shape is a 4-1-4-1, though they have also used 4-3-3. They apply moderate pressing intensity (PPDA 17.8). They are selective in their shooting (10.1 per 90).
Saudi Arabia will need to leverage their strengths while managing the physical demands of a tournament spread across three host countries. With Georgios Donis appointed relatively recently (161 days before kickoff), building tactical cohesion in limited preparation time is the immediate challenge.
Cape Verde historically converts 16.1% of xG from set-pieces, contributing 0.14 expected set-piece goals in this fixture. Combined, the model expects 0.14 set-piece goals across the 90 minutes.
- P(Cape Verde scores set-piece goal) 12.8%
- P(set-piece goal in match) 12.8%
If a penalty is awarded to Cape Verde, the model gives 72.0% conversion, 70.0% for Saudi Arabia.
Cape Verde primary PK: Nuno da Costa (1/1 in 2018-19, per fbref 2018 19).
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.
Tactical forecast
- PPDA
- 17.2
- Possession
- 53%
- Directness (yds/pass)
- 6.6
- Long balls/90
- 37
- Set-piece xG
- 16%
- PPDA
- 17.8
- Possession
- 52%
- Directness (yds/pass)
- 6.2
- Long balls/90
- 36
- Set-piece xG
- —
Style profile per side from StatsBomb open-data aggregation across recent international tournaments (Euro 2020/2024, Copa America 2024, AFCON 2023, World Cup 2018/2022). The tactical-fingerprint badge maps each team’s observed style vector into one of eight canonical archetypes via a rule-based classifier; teams with fewer than three matches of qualifying coverage carry an “insufficient-data” label rather than being forced into a default. Sides outside the StatsBomb-open corpus use FotMob team match stats from recent qualifiers and friendlies instead (possession and shot volume only), marked as partial coverage. PPDA = passes the side allows per defensive action (lower = more intense press). Formation distributions are not yet produced — that head of the §2.7 classifier is pending its own data pull. See /docs/methodology/.
Squad depth
Most irreplaceable starters
Cape Verde
- Logan CostaCentre-backCover: Diney · 0.360.41gap
- Kevin PinaDefensive midfieldCover: Laros Duarte · 0.280.25gap
- Jamiro MonteiroCentral midfieldCover: Yannick Semedo · 0.130.24gap
Saudi Arabia
- Firas Al-BuraikanStrikerCover: Abdullah Al-Salem · 0.050.51gap
- Abdullah Al-HamdanStrikerCover: Abdullah Al-Salem · 0.050.30gap
- Salem Al-DawsariWingerCover: Saleh Abu Al-Shamat · 0.030.29gap
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 level13 m
- Avg temperatureFive-year mean over the tournament window28.4 °C
- Avg humidity78%
- Heat stressShade WBGT ~31.8 °CHigh heat stress
- Pitch surfacetemporary natural grass over artificial turf
Indoor artificial-turf stadium laying a temporary natural-grass 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)
- Nuno da CostaPKFW6.6%
- Dailon LivramentoFW8.0%
- Ryan MendesFW8.0%
- Abdullah Al-HamdanFW5.3%
- Firas Al-BuraikanFW5.3%
- Saleh Al-ShehriFW5.3%
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
Cape Verde
vs Argentina · avg 7.0
Saudi Arabia
vs Spain · avg 3.7
Worked well: Not observable from highlights
Struggled: Not observable from highlights
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.
8DA COSTAScored two crucial goals with clinical finishing from inside the box.
Scored two crucial goals with clinical finishing from inside the box.
7Nuno da Costa111'–142'Was a persistent attacking threat, forcing multiple good saves from the goalkeeper.
1goals3shots3on target▼
Was a persistent attacking threat, forcing multiple good saves from the goalkeeper.
Match timeline
6Semedo14'–19'Involved in multiple attacking sequences, demonstrating a willingness to shoot but lacked precision.
2shots1on target▼
Involved in multiple attacking sequences, demonstrating a willingness to shoot but lacked precision.
Match timeline
6Ryan Mendes53'–53'Contributed to the attack by getting a shot on target, though it was blocked.
1shots▼
Contributed to the attack by getting a shot on target, though it was blocked.
Match timeline
6Duarte127'–127'Attempted a shot that was blocked, contributing to the team's offensive efforts.
1shots▼
Attempted a shot that was blocked, contributing to the team's offensive efforts.
Match timeline
5VozinhaMade several diving saves but ultimately conceded multiple goals.
1saves▼
Made several diving saves but ultimately conceded multiple goals.
Match timeline
8Al-Owais19'–142'Made numerous crucial saves to keep his team in the game despite sustained pressure.
7saves▼
Made numerous crucial saves to keep his team in the game despite sustained pressure.
Match timeline
6Al-ShammariHad a shot on target that was saved by the opposing goalkeeper.
Had a shot on target that was saved by the opposing goalkeeper.
6CHAKHTIContributed to offensive movements and provided support in the final third.
Contributed to offensive movements and provided support in the final third.
Match observations
- The match was a hard-fought contest with Cape Verde dominating attacking opportunities, particularly in the final third.
- Saudi Arabia's goalkeeper, Al-Owais, was a standout performer, making numerous important stops to deny Cape Verde a breakthrough.
- Despite the scoreboard showing 0-0 throughout the match action, Cape Verde's jubilant celebration at the end, coupled with commentary, indicates they secured a victory and progressed to the knockout phase.
▸Under the hood
Model-by-model comparison
Cape Verde vs Saudi Arabia
| Model | Weight | Home | Draw | Away |
|---|---|---|---|---|
| EloRating-based strength estimate | 32% | 38.9% | 22.0% | 39.1% |
| Dixon-ColesGoal-process model with low-score correction | 63% | 31.9% | 35.4% | 32.6% |
| Hierarchical PoissonBayesian model with confederation pooling | 6% | 33.2% | 34.4% | 32.4% |
| Bayesian stackingLearned-weight combination | — | 33.2% | 36.0% | 30.8% |
| Ensemble (published)Uniform average + isotonic calibration | — | 33.3% | 34.1% | 32.6% |
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
Probability decomposition (transparency surface)
- Baseline ensemble — P(Cape Verde win)30.6%
- + Lineup contribution0.0pp
- + Style-matchup contribution0.0pp
- Published P(Cape Verde win)30.6%
Decomposition of the published P(Cape Verde win) into the calibrated- baseline plus contributions from the §2.3 expected-XI lineup delta and the §2.7 style-matchup interaction. The §2.7 roadmap is explicit that style effects are second-order to team strength — single-digit-percentage P(win) shifts on extreme style matchups, near-zero on balanced ones. We surface the decomposition for transparency even when the contributions are small; the baseline carries the prediction. Methodology: /docs/methodology.
For this fixture both contributions round to under 0.05pp — the fitted style-matchup pair effect is in the small-magnitude regime the model expects to dominate.
Latest news & match context
No recent headlines for Cape Verde or Saudi Arabia.
- Stage:
- Group H · Matchday 3
- Date:
- 26 Jun
Cape Verde
Cape Verde come in at close to full strength.
Saudi Arabia
Saudi Arabia come in at close to full strength.
Cape Verde and Saudi Arabia 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
This match is a free preview
You're seeing the model's full forecast for this fixture for free. Unlock the same depth: probabilities, expected goals, scoreline distributions, and per-player scoring, for all 104 matches with a Standard Pass, valid through the tournament.
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.