Scoreline picks that maximise contest points — not headlines. [ market 60% · form 25% · xG 15% · ranking 15% · last-match v2 ]
FIFA № 2 (~1875 pts) — vs — FIFA № 9 (~1742 pts)
An irresistible-force fixture: Spain have kept a clean sheet in all five games — no goal conceded in over ten hours, 0.30 xGA/game, the stingiest run ever recorded at a World Cup — while Belgium arrive on 21.4 shots a game, 13 goals, and De Ketelaere's breakout (2G+1A v the USA). Something gives. The model says it's the shutout: Belgium's volume (2.20 xG/game) is real, and with Onana out (ACL) and Trossard nursing a muscle complaint, 2–1 Spain shades 2–0 by a rounding error. Spain are unbeaten in eleven against Belgium; the last five went 13–1 on aggregate. FT 2–1 ★ — called to the goal: Fabián Ruiz slotted a rebound (30′), De Ketelaere ended Spain’s record shutout run (41′), and with extra time looming Merino pounced on Lammens’ spill (88′). Something gave — exactly the way the model said: the streak bent, Spain won by one. Full +40, our third exact of the knockouts.
Grid covers 95.9% of outcomes · over 2.5 goals: 54.0% · 90-minute scoreline
| Score | P(exact) | E[points] |
|---|---|---|
| 2–1◂ PLAY | 9.9% | 8.37 |
| 2–0 | 9.6% | 8.30 |
| 1–0 | 8.8% | 8.06 |
| 3–1 | 6.0% | 7.20 |
| 3–0 | 5.8% | 7.16 |
| 1–1 | 12.6% | 6.43 |
Start from the de-vigged closing market (60%), then blend twelve-month form & style (25%), an in-tournament xG model (15%) rating each team on the expected goals it created & conceded across its four games so far, and the FIFA ranking's Elo expectancy (15%). The xG signal is shrunk to the league mean so it nudges rather than dictates.
Each team's xG is nudged by how its most recent game beat/missed expectation; the attack term (finishing) is halved because it regresses. The read uses each side's final group game — now a week old for today's slate, so treat it as a light thumb on the scale.
A Poisson model with the Dixon-Coles low-score correction ρ gives a probability for every scoreline. Each is ranked by 30·P(exact) + 10·P(1X2) — the contest's scoring, which stack (an exact hit is worth 40). Knockouts are scored on the 90-minute result, so the model still picks within 90 minutes.
Quarter-finals, Day 2 — graded: EXACT, +40 ★. Spain 2–1 Belgium played out to the letter: Belgium’s volume ended the record clean-sheet run (De Ketelaere 41′), and Spain won by one via Merino’s 88′ rebound. Transparency note: no bulletin was published for Saturday’s quarter-finals — England 2–1 Norway (AET, 1–1 at 90′) and Argentina 3–1 Switzerland (AET) went unpicked, and the ledger counts those 80 possible points as missed (0/80). Tournament 930/3960. The semifinals: France–Spain in Dallas, England–Argentina to follow. Scoring: 30 exact · 10 winner (max 40).
Across 24 graded knockout picks: the model said 25% of games end level after ninety — 25% did (6 of 24). It projected 2.62 goals a game — 2.65 arrived. It claimed ~12.9% on its exact picks and landed 8.3% (2 of 24) — inside one standard error at this sample size. Nothing in the data says the probabilities are wrong.
Knockout haul: 210 of 960 (21.9% of max) against the model's own pre-match expectation of ~21%. Results hit 15/24 (win-picks 14/20 = 70%); two exacts ★ (Canada 0–1, Colombia 1–0). The actual scoreline landed in our published top-three 55% of the time against a modelled 33% — the grid's shape has been better than advertised; the top line has been unlucky within it.
Variance dominates at n=24. Two behavioural rules survive the audit: coin-flip draw picks stay (the draw share was priced exactly right), and no exact-chasing — the second-ranked scoreline has cashed five times to the top line's one, a gap comfortably inside luck; abandoning the E[pts] argmax would trade points for stories. Eight picks remain (four quarter-finals, two semis, the bronze final and the final): expected haul ≈ +70, projected finish ≈ 950/4120.