How match previews work

What the reader sees

Every fixture page now opens with a structured prose summary covering:

1. Headline expected shape. Favoured side, Dixon-Coles λ_home and λ_away, P(H/D/A), modal scoreline.
2. Predicted formations and key players. One paragraph per side, naming the formation string and the highest-rated player by anytime-scorer model output (Model #5), with a role descriptor derived from squad position (FW → "primary attacking outlet", MF → "creator from midfield", DF → "set-piece / late-runner threat from the back", GK → "goal-line presence").
3. Strategic factors. Whichever of set-piece propensity, weather / altitude, referee tendency, pace differential (Elo gap), and injury notes clear the per-axis meaningfulness thresholds. Below threshold the factor is simply omitted.
4. Set-piece outlook. Per-side set-piece xG share multiplied by the corresponding DC λ to give an expected set-piece-goals number.

…