Group F · Matchday 2
JapanvsTunisia
2026-06-20·22:00 localPredictions finalised
The forecast
Match-outcome probability
- Japan win54.6%
- Draw27.7%
- Tunisia win17.7%
A 268-point Elo gap frames this as a significant mismatch, yet the model still gives Tunisia a 14% probability of a result — enough to make this more than a formality.
Why the model says this
Favoring Japan
- ·Japan holds a significant Elo advantage of 268 points over Tunisia.
- ·Japan is ranked 18th globally by FIFA, significantly higher than Tunisia's 40th position.
- ·Japan's expected goals (xG) of 1.3 is considerably higher than Tunisia's 0.76.
- ·Japan has won 4 of the 5 historical encounters against Tunisia, with 0 draws.
Favoring Tunisia
- ·Tunisia secured a 3-0 victory in the most recent encounter in the Kirin Cup on 2022-06-14.
- ·Tunisia has kept 2 clean sheets in their last 6 matches, including a 0-0 draw in their most recent fixture.
- ·Tunisia exhibits a high reliance on set-pieces, with 26.3% of their xG coming from such situations, placing them in the 98.7 percentile.
What the model can't fully price
- ·The model does not account for the 3 players carrying fitness doubts across both squads, including 1 projected starter.
- ·No specific venue or city information is provided, so the model cannot account for potential travel fatigue or home advantage factors.
Form check
Japan
ImprovingJapan enters this match in exceptional form, having won 5 of their last 6 fixtures and drawing the other. They have demonstrated strong defensive solidity, conceding only 4 goals in this period.
5 clean sheets in their last 6 matches
Tunisia
SteadyTunisia's recent form is mixed, with 2 wins, 3 draws, and 1 loss in their last 6 games. They have shown resilience with multiple draws but also conceded 3 goals in one of their recent African Cup of Nations matches.
3 draws in their last 6 matches
Analysis
How it plays out
Japan defend deep and give Tunisia the ball. The question is whether Tunisia's pragmatic approach generates enough final-third creativity to break through. Tunisia's aggressive press (PPDA 22.5) against Japan's deeper build-up (PPDA 26.7) creates a clear territory question: can Tunisia force errors high up, or will Japan play through the press and find space behind it? Tunisia generate 26% of their xG from set pieces. Foul discipline and aerial duels from Japan matter more here than usual.
What decides it
Japan defend deep and limit space. Set pieces and individual errors become the most likely routes to goal. Tunisia adjust shape to the opponent. That flexibility is an asset, but it takes longer to settle into a game. The scoring threat is evenly split: Daichi Kamada (6.2%) and Dylan Bronn (5.3%).
Off the pitch
Hajime Moriyasu (8 years in charge of Japan) vs Sabri Lamouchi (0 years). That tenure gap shows up in squad familiarity and set-piece coordination.
The angle
Likely the last World Cup for Yūto Nagatomo. Tournament experience at this level is hard to quantify but hard to replace.
▸Goals & scorelines
Likeliest score 1–0 (16.9%) · xG 1.3 - 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
- 1–016.9%
- 0–014.5%
- 1–113.1%
- 2–011.3%
- 0–18.9%
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
- 0–037.5%
- 1–023.3%
- 0–112.5%
- 1–18.9%
- 2–07.6%
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 goals85.5%
- More than 1.5 goals59.8%
- More than 2.5 goals32.0%
- More than 3.5 goals14.0%
- More than 4.5 goals5.1%
- More than 5.5 goals1.6%
- Both teams score37.2%
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
- Japan clean sheetOpposing team scores zero49.5%
- Tunisia clean sheetOpposing team scores zero27.7%
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
- Japan by 4+2.4%
- Japan by 3+8.5%
- Japan by 2+23.6%
- Japan by 1+49.7%
- Draw30.7%
- Tunisia by 1+19.7%
- Tunisia by 2+5.7%
- Tunisia by 3+1.2%
- Tunisia by 4+0.2%
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 32.0% · BTTS 37.2%
Game state through the match
- Japan ahead50.4%
- Level29.2%
- Tunisia ahead20.4%
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
- 0–1528.2%
- 15–3020.2%
- 30–4514.5%
- 45–6010.4%
- 60–757.5%
- 75–905.4%
- No goal13.7%
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 → | HJapan win | DDraw | ATunisia win |
|---|---|---|---|
| HJapan ahead | 31.6% | 4.0% | 0.8% |
| DLevel | 17.3% | 21.5% | 8.1% |
| ATunisia ahead | 1.5% | 3.9% | 11.4% |
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
- Japan trail at HT, avoid defeat at FT5.4%
- Tunisia trail at HT, avoid defeat at FT4.7%
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: Kamada (6.2%)
Match detail
Japan
Model-rated key players: Daichi Kamada (MF) — P(scores) 6.2%; Ayase Ueda (FW) — P(scores) 2.7%; Daizen Maeda (FW) — P(scores) 2.3%.
Japan under Hajime Moriyasu play a low block game, with just 44% possession — among the lowest in the field. Their likely shape is a 4-2-3-1, though they have also used other. They sit deeper and pick their moments to press (PPDA 26.7).
Japan will look to stay compact and frustrate opponents, limiting space and hitting on the break. Set-piece proficiency — both attacking and defending — becomes critical when open-play chances are limited by design. Managing minutes for Yūto Nagatomo across what could be seven matches will test the coaching staff's rotation planning.
Tunisia
Model-rated key players: Dylan Bronn (DF) — P(scores) 5.3%; Seifeddine Jaziri (FW) — P(scores) 5.6%; Elias Achouri (FW) — P(scores) 4.4%.
Tunisia under Sabri Lamouchi play a pragmatic game with 49% possession. Their likely shape is a other. They apply moderate pressing intensity (PPDA 22.5). They are selective in their shooting (9.8 per 90) and rely heavily on set pieces (26% of their xG).
Tunisia 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. With Sabri Lamouchi appointed relatively recently (161 days before kickoff), building tactical cohesion in limited preparation time is the immediate challenge.
Japan historically converts 6.3% of xG from set-pieces, contributing 0.08 expected set-piece goals in this fixture. Tunisia converts 26.3% from set-pieces (0.18 expected). Combined, the model expects 0.27 set-piece goals across the 90 minutes.
- P(Japan scores set-piece goal) 7.8%
- P(Tunisia scores set-piece goal) 16.9%
- P(set-piece goal in match) 23.4%
Japan: Takefusa Kubo on corners (18 corners), Daichi Kamada on free kicks (per fbref 2022 23) · Tunisia: Naïm Sliti on corners (95 corners) (per fbref 2018 19)
If a penalty is awarded to Japan, the model gives 71.4% conversion, 71.4% for Tunisia.
Japan primary PK: Daichi Kamada (2/2 in 2022-23, per fbref 2022 23) · Tunisia primary PK: Dylan Bronn (1/2 in 2020-21, 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
- 26.7
- Possession
- 44%
- Directness (yds/pass)
- 6.5
- Long balls/90
- 35
- Set-piece xG
- 6%
- PPDA
- 22.5
- Possession
- 49%
- Directness (yds/pass)
- 6.7
- Long balls/90
- 40
- Set-piece xG
- 26%
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
Japan
- Ayase UedaStrikerCover: Yuito Suzuki · 0.310.34gap
- Kōki OgawaStrikerCover: Yuito Suzuki · 0.310.14gap
- Takefusa KuboWingerCover: Keito Nakamura · 0.590.13gap
Tunisia
- Montassar TalbiCentre-backCover: Adem Arous · 0.060.62gap
- Dylan BronnCentre-backCover: Adem Arous · 0.060.53gap
- Hannibal MejbriAttacking midfieldNo natural backup0.37gap
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 level521 m
- Avg temperatureFive-year mean over the tournament window27.7 °C
- Avg humidity65%
- Heat stressShade WBGT ~29.1 °CModerate heat stress
- Pitch surfacenatural grass
Natural-grass football stadium; the pitch was refreshed ahead of 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. Night 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)
- Daichi KamadaPKMF6.2%
- Ayase UedaFW2.7%
- Daizen MaedaFW2.3%
- Dylan BronnPKDF5.3%
- Seifeddine JaziriFW5.6%
- Elias AchouriFW4.4%
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
Japan
vs Brazil · avg 6.7
Tunisia
vs Netherlands · avg 7.5
Worked well: Their offensive movement and finishing were highly effective, resulting in four well-taken goals. They maintained strong pressure and created many chances.
Struggled: While dominant, there were moments where they could have been more decisive in the box, as seen with Nakamura's hesitation and Dahmen's saves.
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.
8Daichi Kamada0'–0'Scored the crucial opening goal with excellent positioning and a clinical finish.
1goals▼
Scored the crucial opening goal with excellent positioning and a clinical finish.
Match timeline
8Ritsu DoanScored a fantastic second goal with a powerful and accurate shot from outside the box.
Scored a fantastic second goal with a powerful and accurate shot from outside the box.
8Junya ItoScored the third goal with a composed finish after a well-timed run onto a through ball.
Scored the third goal with a composed finish after a well-timed run onto a through ball.
7Ayase Ueda0'–0'Tapped in the fourth goal from close range, demonstrating good positioning and striker's instinct.
1goals▼
Tapped in the fourth goal from close range, demonstrating good positioning and striker's instinct.
Match timeline
7Zion Suzuki0'–0'Made a crucial early save and contributed to Japan's clean sheet.
1saves▼
Made a crucial early save and contributed to Japan's clean sheet.
Match timeline
6Ao Tanaka0'–0'Contributed to Japan's offensive efforts with a shot from distance that was saved.
1shots1on target▼
Contributed to Japan's offensive efforts with a shot from distance that was saved.
Match timeline
8Mouez DahmenMade multiple outstanding and crucial saves, including a goal-line stop, preventing an even larger defeat for Tunisia.
Made multiple outstanding and crucial saves, including a goal-line stop, preventing an even larger defeat for Tunisia.
Match observations
- Japan delivered a dominant performance, securing a comprehensive 4-0 victory over Tunisia.
- The match saw Japan's attacking players display clinical finishing, converting their chances effectively.
- Tunisia's goalkeeper, Mouez Dahmen, was a standout performer for his side, making numerous crucial saves to limit the scoreline.
▸Under the hood
Model-by-model comparison
Japan vs Tunisia
| Model | Weight | Home | Draw | Away |
|---|---|---|---|---|
| EloRating-based strength estimate | 32% | 72.2% | 22.0% | 5.8% |
| Dixon-ColesGoal-process model with low-score correction | 63% | 50.7% | 29.9% | 19.3% |
| Hierarchical PoissonBayesian model with confederation pooling | 6% | 51.1% | 28.9% | 20.0% |
| Bayesian stackingLearned-weight combination | — | 62.4% | 30.1% | 7.5% |
| Ensemble (published)Uniform average + isotonic calibration | — | 57.5% | 28.4% | 14.1% |
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
Probability decomposition (transparency surface)
- Baseline ensemble — P(Japan win)54.6%
- + Lineup contribution0.0pp
- + Style-matchup contribution0.0pp
- Published P(Japan win)54.6%
Decomposition of the published P(Japan 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 |
|---|---|---|---|---|---|
| 20 Jun 2026 | FIFA World Cup | NGuadalupe | 4–0 | W | — |
| 14 Jun 2022 | Kirin Cup | HSuita | 0–3 | L | — |
| 27 Mar 2015 | Kirin Challenge Cup | HŌita | 2–0 | W | — |
| 8 Oct 2003 | Friendly | ATunis | 1–0 | W | — |
| 14 Jun 2002 | FIFA World Cup | HOsaka | 2–0 | W | — |
| 13 Oct 1996 | Friendly | HKobe | 1–0 | W | — |
Japan vs Tunisia, every senior international meeting in the martj42 results dataset (score from Japan's perspective; H/A/N = home/away/neutral).
Latest news & match context
No recent headlines for Japan or Tunisia.
- Stage:
- Group F · Matchday 2
- Date:
- 20 Jun
Ranked by likely importance. None of these feed the forecast: the probabilities rest on team strength, venue conditions and the style matchup.
- 1.Squad availability: 1 carrying a fitness doubt across the two squads. The forecast does not adjust for who is missing: its lineup channel currently contributes zero, so this is context the probabilities do not include.
Japan
Japan: 1 carrying a fitness doubt.
- DoubtWataru Endo (midfielder) is carrying Foot injury — a depth-level fitness watch item.
Tunisia
Tunisia come in at close to full strength.
Both projected XIs look intact; the fitness concerns are at squad-depth level rather than among first-choice starters.
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.