Southampton FC scores shown first. Bivariate Poisson with team xG from recent form — most-likely score ≠ most-likely winner.
Probabilities derived from a Poisson model on expected goals. Edge % shown only when the book posts both sides of a market.
Joint probability comes from the score grid (the truth). Naïve is what a book gets by multiplying legs — they undershoot correlated positive legs like "home + BTTS" and overshoot anti-correlated ones like "draw + over 2.5". Buy positive correlation; avoid negative.
Model probabilities Southampton FC 20.5% · Draw 19.3% · Queens Park Rangers FC 60.3% Why Queens Park Rangers FC is favoured Queens Park Rangers FC's Elo (1541) is +185 over Southampton FC (1356); low confidence. Recent: Southampton FC 6W-3D-1L · Queens Park Rangers FC 4W-4D-2L (last 10). Goal differential per game: Southampton FC +1.1, Queens Park Rangers FC +0.6. Form depth Southampton FC: avg 2.0 goals scored, 0.9 conceded per game (4/5 at home, 2/5 on the road). Queens Park Rangers FC: avg 1.7 goals scored, 1.1 conceded per game (3/5 at home, 1/5 on the road). Goals expectation Model expects ~2.9 total goals (Southampton FC 1.6, Queens Park Rangers FC 1.3) — above the 2.5-goal mid line. But — counter-arguments Southampton FC has a stronger recent record (60% vs 40%) — model favours Queens Park Rangers FC on Elo despite Southampton FC's form. Elo confidence is low (25%) — ratings are based on a thin sample, so the prediction itself is wider than the headline number suggests. Calibration Raw model: 25.3% home · Platt-calibrated down to 20.5% based on historical reliability across this sport's graded matches. Confidence note Elo data on these teams is thin (25% sample-size confidence); headline number is sharper than the underlying signal — treat it as directional, not absolute.