Scoreline picks that maximise contest points — not headlines. [ market 60% · form 25% · xG 15% · ranking 15% · last-match v2 ]
FIFA № 4 (~1828 pts) — vs — FIFA № 1 (~1877 pts)
Maradona ’86, Beckham ’98, Beckham again in ’02 — and now Atlanta. The world champions, with Messi (39, 8 goals, probably his last World Cup) against an England side chasing a first final since 1966 behind Bellingham & Kane (6 each). The blend lands on a dead-even 35/30/35 — and both these teams stood at 1–1 after ninety in their quarter-finals before winning in extra time. Argentina’s legs carry 240 ET minutes; England’s Quansah ban ends only for the final. The Under is juiced (1.61) and 1–1 leads the ledger by 1.4 expected points — the clearest draw signal of the tournament. Fifth and biggest coin-flip draw pick. FT 1–2 — alive until stoppage: Gordon tapped England ahead (55′), Enzo Fernández thundered the equaliser (85′), and our 1–1 stood at 90:00 — then Lautaro Martínez headed Messi’s cross in at 90+2′. Both Argentina goals from Messi deliveries; the champions reach a second straight final, and the draw pick dies inside stoppage time. 0 pts.
Grid covers 97.6% of outcomes · over 2.5 goals: 50.1% · 90-minute scoreline
| Score | P(exact) | E[points] |
|---|---|---|
| 1–1◂ PLAY | 14.4% | 7.35 |
| 2–1 | 8.3% | 5.99 |
| 1–2 | 8.2% | 5.94 |
| 0–0 | 9.0% | 5.72 |
| 1–0 | 7.1% | 5.64 |
| 0–1 | 7.0% | 5.59 |
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.
Semifinals, Day 2 — graded: 0, by two minutes of stoppage. England 1–2 Argentina: Gordon (55′), Enzo Fernández’s 85′ rocket, and the 1–1 we picked was the live score at the ninety — until Lautaro Martínez met Messi’s cross at 90+2′. Messi assisted both; Argentina meet Spain in Sunday’s final. The five knockout draw picks close 1-for-5 — each priced fairly, four undone by single moments. Tournament 930/4040. Saturday: the bronze final, France–England in Miami. 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.