2026 World Cup · Score Research

07-07 08:00 CST · World Cup Group Stage · Separate HT/FT models

USA

Home side / left market direction

Full-time first pick 1:1 Probability 16.6% · Standard score cluster Standard score cluster: 1:1 16.6%; 2:1 14.7%; 2:2 9.5%; 1:2 10.5% Half-time first pick 0:0 (62.5%)

Belgium

Away side / right market direction

Five-Factor Read

1. Market strength USA side rates higher

The Asian handicap is close to level, with no clear market gap.

2. Form and pace 0:0

HT first pick is 0:0 (62.5%); HT draw probability is 66.2%, so the model still respects early caution.

3. H2H and goal environment FT total 2.75

This match uses a team-style adjustment: historical goals for, goals against and match tempo classify the teams' attacking or defensive tendency. The signal only reweights candidate scores and does not override the market baseline by itself.

4. Venue factor host edge / normal weather

Venue: 西雅图体育场. Non-neutral venue. Weather/temperature: 天晴, 25℃～26℃. USA has a domestic-tournament setting here; treat it as a small crowd/familiarity edge, not a standalone reason to override the market. Weather and temperature do not show a clear tempo-suppression signal. Together with the totals line, the venue layer can support a more open upper tail.

5. Sample and soft factors Usable sample

218 comparable matches; useful for probability ranking

Full-Time Score Distribution

1:1 16.6%

2:1 14.7%

2:2 9.5%

1:2 10.5%

1:3 6.9%

3:2 4.8%

3:1 4.8%

2:3 4.1%

FT market: side line 0.00 · total 2.75 · Bucket ah_ou:0.0/3.0

Score cluster: Standard score cluster: 1:1 16.6%; 2:1 14.7%; 2:2 9.5%; 1:2 10.5%

Half-Time Score Distribution

0:0 62.5%

1:0 14.6%

0:1 13.6%

1:1 3.6%

2:0 1.9%

0:2 1.8%

2:1 0.6%

1:2 0.6%

HT market: side line 0.00 · total 1.00

USA win37.5%

Draw30.0%

Belgium win32.5%

USA expected goals1.78

Belgium expected goals1.71

Under 3.554.5%

FT temperature0.95

Empirical weight73.2%

Sample size218

Europe 1X2home 38.2% / draw 28.6% / away 33.3%

Key Variables

First-goal path USA benefits most from opening the scoring; if HT stays 0:0, the FT distribution compresses toward lower scores.

Deciding factor Draw probability is 30.0%, so the exact-score set should keep draw and one-goal-margin scripts alive.

Risk point Under 3.5 is 54.5%; if the live total moves up materially, rerun the model.

Pre-Match Update · Market Movement

Published 2026-07-07 07:00:01 CST (started/finished about 689h 20m ago) | Snapshot window: 2026-07-02 12:00:01 -> 2026-07-07 07:00:01

First snapshotFT handicap 0 · total 2.75

Latest marketFT handicap 0 · total 2.75

Movement: FT handicap held at 0; FT total held at 2.75; HT handicap held at 0; HT total held at 1.

Pre-match note: Market movement is limited; keep the model ranking unless late odds or lineups change materially.

Final Read: 1:1

Predicted side: USA win · Actual side: Belgium win · side missed

Using the full-time handicap, totals, comparable market buckets and half-time market, the model's full-time first pick for USA vs Belgium is 1:1 (16.6%). USA side rates higher. This match uses a team-style adjustment: historical goals for, goals against and match tempo classify the teams' attacking or defensive tendency. The signal only reweights candidate scores and does not override the market baseline by itself. HT first pick is 0:0 (62.5%); HT draw probability is 66.2%, so the model still respects early caution. Exact-score outputs are probability rankings for pre-match research and review.

Risk note: exact scores are low-hit-rate events. The model output is a probability ranking, not a certainty; late market moves, lineups, red cards and early goals can reshape the distribution.

Sources

Feijing · schedule, results, Asian handicap, totals, half-time markets, Europe 1X2 · Local history database · historical market lines, full-time scores, half-time scores · DeepSeek · AI sidecar context, bounded candidate reweighting only · RotoWire · World Cup lineups, injuries and weather context · Wikipedia · group structure, advancement rules and schedule cross-checks