Premier League · Score Research

08-22 19:30 CST · Premier League · Separate HT/FT models

Hull City

Home side / left market direction

Full-time first pick 1:2 Probability 12.4% · High-total score cluster High-total score cluster: 1:2 12.4%; 1:3 7.2%; 0:3 6.9%; 1:4 5.9%; 2:3 4.2%; 0:4 3.7%; 2:4 1.8%; 0:5 1.6% Half-time first pick 0:0 (44.8%)

Manchester United

Away side / right market direction

Five-Factor Read

1. Market strength Manchester United side rates higher

The handicap leans toward Manchester United; the market prices the away side as stronger.

2. Form and pace 0:0

HT first pick is 0:0 (44.8%); HT draw probability is 52.5%, so the model still respects early caution.

3. AI Sidecar Read FT total 3.00

This match uses a DeepSeek AI sidecar factor. The AI signal only applies a small candidate-score reweighting and does not override the market/history main model by itself. AI note: 曼联实力占优但杯赛可能轮换，指数让球深但模型最佳比分仅赢一球，存在赢球输盘风险；赫尔城主场或偷分。

4. Venue factor non-neutral / normal weather

Venue: 金斯顿通信球场. Non-neutral venue. Weather/temperature: 间中有云, 17℃～18℃. The schedule marks this as non-neutral, so home/away identity remains a weak background factor. 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 Thin sample

29 comparable matches; manual review needed

Full-Time Score Distribution

1:2 12.4%

1:1 11.5%

0:2 9.2%

0:1 8.3%

1:3 7.2%

0:3 6.9%

1:4 5.9%

2:2 4.6%

FT market: side line -1.50 · total 3.00 · Bucket ah_ou:-1.5/3.0

Score cluster: High-total score cluster: 1:2 12.4%; 1:3 7.2%; 0:3 6.9%; 1:4 5.9%; 2:3 4.2%; 0:4 3.7%; 2:4 1.8%; 0:5 1.6%

Half-Time Score Distribution

0:0 44.8%

0:1 24.3%

1:0 9.7%

0:2 7.7%

1:1 7.5%

1:2 1.8%

0:3 1.4%

2:0 1.0%

HT market: side line -0.50 · total 1.25

Hull City win13.3%

Draw20.4%

Manchester United win66.3%

Hull City expected goals0.98

Manchester United expected goals2.25

Under 3.560.2%

FT temperature0.95

Empirical weight26.6%

Sample size29

Europe 1X2home 11.3% / draw 17.7% / away 71.0%

Key Variables

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

Deciding factor Draw probability is 20.4%, so the exact-score set should keep draw and one-goal-margin scripts alive.

Risk point Under 3.5 is 60.2%; if the live total moves up materially, rerun the model.

Pre-Match Update · Market Movement

Published 2026-08-25 00:37:40 CST (started/finished about 53h 8m ago) | Snapshot window: pending -> 2026-08-25 00:37:40

First snapshotFT handicap 待补 · total 待补

Latest marketFT handicap -1.5 · total 3

Movement: FT handicap data pending; FT total data pending; HT handicap data pending; HT total data pending.

Pre-match note: Market snapshots are thin; refresh Feijing data again before publishing the final pre-match version.

Final Read: 1:2

Predicted side: Manchester United win · Actual side: Hull City win · side missed

Using the full-time handicap, totals, comparable market buckets and half-time market, the model's full-time first pick for Hull City vs Manchester United is 1:2 (12.4%). Manchester United side rates higher. This match uses a DeepSeek AI sidecar factor. The AI signal only applies a small candidate-score reweighting and does not override the market/history main model by itself. AI note: 曼联实力占优但杯赛可能轮换，指数让球深但模型最佳比分仅赢一球，存在赢球输盘风险；赫尔城主场或偷分。 HT first pick is 0:0 (44.8%); HT draw probability is 52.5%, 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 · fixtures, 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