Group L · Matchday 2
CroatiavsPanama
2026-06-23·19:00 localPredictions finalised
The forecast
Match-outcome probability
- Croatia win60.0%
- Draw24.3%
- Panama win15.7%
A clash of identities: Croatia's structured-press approach meets Panama's transition-heavy style in a fixture the model gives to Croatia at 74%.
Why the model says this
Favoring Croatia
- ·Croatia holds a significant Elo advantage of 193 points over Panama.
- ·Croatia is ranked 10th in FIFA rankings, significantly higher than Panama's 30th position.
- ·Croatia's expected goals (xG) of 2.03 are substantially higher than Panama's 0.68, indicating a strong offensive projection.
- ·Multiple underlying models show strong favour for Croatia, with the DC model predicting a 68.4% win probability and the HP model predicting 70.3%.
Favoring Panama
- ·Panama has scored 10 goals in their last 6 matches, averaging 1.67 goals per game.
- ·Panama has conceded 6 goals in their last 6 matches, averaging 1.0 goals per game.
- ·Panama has secured 3 wins and 2 draws in their last 6 fixtures.
What the model can't fully price
- ·The model does not account for the impact of squad availability, with 3 players across both teams currently carrying fitness doubts (2 for Croatia, 1 for Panama).
Form check
Croatia
SteadyCroatia enters this match in strong form, having won 4 of their last 6 fixtures, including three consecutive FIFA World Cup qualification victories. Their only loss in this period was a 3-1 friendly defeat.
4 wins in their last 6 matches
Panama
SteadyPanama has shown solid recent form, recording 3 wins and 2 draws in their last 6 outings. They have consistently found the net, scoring 10 goals in this period, but also conceded in 4 of those matches.
Scored 10 goals in their last 6 matches
Analysis
How it plays out
Croatia's high press against Panama's transition game. Panama will try to absorb the press and release quick, so the battle is in the first 10 seconds after each turnover. Croatia will expect to hold 54% possession. Panama need their shape to stay compact without the ball and be clinical when they win it back.
What decides it
Croatia press high (PPDA 20.4). If the press doesn't win the ball early, the space behind their back line becomes exposed. Panama will concede possession willingly and attack in transition. Their defensive block needs to hold without fouling in dangerous areas. Ante Budimir's 9.8% scoring probability is the highest in this fixture. Containing that output is Panama's primary defensive task.
Off the pitch
No major off-pitch asymmetries. This one is decided by the football.
The angle
Likely the last World Cup for Ivan Perišić. Tournament experience at this level is hard to quantify but hard to replace.
▸Goals & scorelines
Likeliest score 2–0 (14.0%) · xG 2.0 - 0.7
Expected goals
Mean of the Dixon-Coles joint goal distribution. Same fit that produces the most-likely-scoreline list below.
Most likely scorelines
- 2–014.0%
- 1–013.5%
- 1–19.8%
- 3–09.3%
- 2–19.2%
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
- 0–027.1%
- 1–025.9%
- 2–013.2%
- 1–19.2%
- 0–18.2%
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 goals92.4%
- More than 1.5 goals74.8%
- More than 2.5 goals49.4%
- More than 3.5 goals27.5%
- More than 4.5 goals13.0%
- More than 5.5 goals5.3%
- Both teams score42.2%
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
- Croatia clean sheetOpposing team scores zero51.8%
- Panama clean sheetOpposing team scores zero13.7%
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
- Croatia by 4+9.3%
- Croatia by 3+22.1%
- Croatia by 2+43.3%
- Croatia by 1+68.3%
- Draw21.0%
- Panama by 1+10.7%
- Panama by 2+2.9%
- Panama by 3+0.5%
- Panama 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.
▸How the match unfolds
Over 2.5 goals 49.4% · BTTS 42.2%
Game state through the match
- Croatia ahead68.8%
- Level19.8%
- Panama ahead11.3%
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
- 0–1535.7%
- 15–3023.0%
- 30–4514.8%
- 45–609.5%
- 60–756.1%
- 75–903.9%
- No goal7.1%
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 → | HCroatia win | DDraw | APanama win |
|---|---|---|---|
| HCroatia ahead | 47.4% | 3.4% | 0.6% |
| DLevel | 19.3% | 13.4% | 4.5% |
| APanama ahead | 2.1% | 3.3% | 6.1% |
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
- Croatia trail at HT, avoid defeat at FT5.4%
- Panama trail at HT, avoid defeat at FT4.0%
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: Budimir (9.8%)
Match detail
Croatia
Model-rated key players: Ante Budimir (FW) — P(scores) 9.8%; Andrej Kramarić (FW) — P(scores) 4.9%; Igor Matanović (FW) — P(scores) 3.3%.
Croatia under Zlatko Dalić play a structured press game, holding 54% of the ball — among the highest in the tournament field. Their likely shape is a 4-3-3, though they have also used 4-2-3-1. They apply moderate pressing intensity (PPDA 20.4) and build patiently through midfield with 7.1 passes per attacking sequence. They favour high-quality chances (xG/shot 0.142, among the best in the field).
Croatia 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. Managing minutes for Ivan Perišić across what could be seven matches will test the coaching staff's rotation planning.
Panama
Model-rated key players: Alfredo Stephens (FW) — P(scores) 3.5%; José Fajardo (FW) — P(scores) 2.4%; Ismael Díaz (FW) — P(scores) 2.1%.
Panama under Thomas Christiansen play a transition heavy game with 46% possession. They apply moderate pressing intensity (PPDA 21.2). They are selective in their shooting (10.0 per 90).
Panama 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 Eric Davis across what could be seven matches will test the coaching staff's rotation planning.
Croatia's predicted XI averages 2,049 club minutes over the 2024-25 season (moderate load).
Croatia coverage: 68.0% (9/11 XI matched against the FBref Big-5) · Panama: 4.0% (1/11).
Croatia historically converts 14.2% of xG from set-pieces, contributing 0.28 expected set-piece goals in this fixture. Combined, the model expects 0.28 set-piece goals across the 90 minutes.
- P(Croatia scores set-piece goal) 24.6%
- P(set-piece goal in match) 24.6%
Croatia: Luka Modrić on corners (15 corners), Kristijan Jakić on free kicks (per fbref 2022 23)
If a penalty is awarded to Croatia, the model gives 75.0% conversion, 72.0% for Panama.
Croatia primary PK: Ante Budimir (2/2 in 2021-22, 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.
Tactical forecast
- PPDA
- 20.4
- Possession
- 54%
- Directness (yds/pass)
- 5.2
- Long balls/90
- 31
- Set-piece xG
- 14%
- PPDA
- 21.2
- Possession
- 46%
- Directness (yds/pass)
- 7.3
- Long balls/90
- 37
- 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
Croatia
- Dominik LivakovićGoalkeeperCover: Ivor Pandur · 0.510.40gap
- Joško GvardiolCentre-backCover: Martin Erlić · 0.690.30gap
- Marin PongračićCentre-backCover: Martin Erlić · 0.690.16gap
Panama
- Adalberto CarrasquillaCentral midfieldNo natural backup0.30gap
- José Luis RodríguezWingerCover: César Yanis · 0.070.28gap
- Ismael DíazWingerCover: César Yanis · 0.070.25gap
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 level78 m
- Avg temperatureFive-year mean over the tournament window21.2 °C
- Avg humidity71%
- Heat stressShade WBGT ~22.9 °CLow heat stress
- Pitch surfacenatural grass
Natural-grass football stadium.
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)
- Ante BudimirPKFW9.8%
- Andrej KramarićFW4.9%
- Igor MatanovićFW3.3%
- Alfredo StephensFW3.5%
- José FajardoFW2.4%
- Ismael DíazFW2.1%
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
Croatia
vs Portugal · avg 7.0
Worked well: Their early goal and continued creation of scoring opportunities demonstrated their offensive capabilities.
Struggled: A significant weakness was their repeated failure to beat the offside trap, resulting in two disallowed goals.
Panama
vs England · avg 7.0
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.
7DigneProvided a solid defensive performance, making crucial tackles and supporting the attack from the left flank.
Provided a solid defensive performance, making crucial tackles and supporting the attack from the left flank.
7BrahimAn influential winger who used his good dribbling skills to create attacking opportunities and pose a threat to the opponent's defense.
An influential winger who used his good dribbling skills to create attacking opportunities and pose a threat to the opponent's defense.
6EndrickAn active forward who contributed to both offensive pressure and defensive recovery, including creating a shooting opportunity.
An active forward who contributed to both offensive pressure and defensive recovery, including creating a shooting opportunity.
6Neymar JrShowed flashes of individual skill on the left wing, contributing to Taif's offensive efforts through dribbling and passing.
Showed flashes of individual skill on the left wing, contributing to Taif's offensive efforts through dribbling and passing.
8Jacobo RamónA strong defensive presence who made vital interventions, including key tackles inside the box, to protect his team's goal.
A strong defensive presence who made vital interventions, including key tackles inside the box, to protect his team's goal.
7BeckhamA diligent midfielder who contributed significantly to rellll's defensive efforts with several effective tackles.
A diligent midfielder who contributed significantly to rellll's defensive efforts with several effective tackles.
Match observations
- The match was an evenly contested affair, with both teams employing an attacking 4-3-3 formation.
- Taif took the lead in the first half through Al Dawsari, but rellll responded in the second half with a goal from Haaland.
- Both sides displayed moments of offensive flair and defensive resilience.
▸Under the hood
Model-by-model comparison
Croatia vs Panama
| Model | Weight | Home | Draw | Away |
|---|---|---|---|---|
| EloRating-based strength estimate | 32% | 67.0% | 22.0% | 11.0% |
| Dixon-ColesGoal-process model with low-score correction | 63% | 68.7% | 20.7% | 10.6% |
| Hierarchical PoissonBayesian model with confederation pooling | 6% | 69.3% | 19.9% | 10.9% |
| Bayesian stackingLearned-weight combination | — | 77.3% | 18.8% | 3.9% |
| Ensemble (published)Uniform average + isotonic calibration | — | 74.0% | 20.6% | 5.5% |
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(Croatia win)64.3%
- + Lineup contribution0.0pp
- + Style-matchup contribution0.0pp
- Published P(Croatia win)64.3%
Decomposition of the published P(Croatia 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.
Head-to-head history
| Date | Competition | Venue | Score | Result | xG |
|---|---|---|---|---|---|
| 23 Jun 2026 | FIFA World Cup | NToronto | 1–0 | W | — |
Croatia vs Panama, every senior international meeting in the martj42 results dataset (score from Croatia's perspective; H/A/N = home/away/neutral).
Latest news & match context
No recent headlines for Croatia or Panama.
- Stage:
- Group L · Matchday 2
- Date:
- 23 Jun
Croatia and Panama 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.