WinPIQKnow Before You Pick.
Sign in
🇺🇸 Showing content for United States · by location · Change21+ only · analysis and probability estimates, not financial advice · help: 1-800-GAMBLER
WinPIQ Lab · Model Room

How WinPIQ thinks

Transparency without giving away the formulas: which model families vote, how they are weighted, what the backtest says, and what changed between versions. No proprietary code, no invented numbers.

ens_v0.1
current model
7
signals used
5
competitions covered
141
matches analyzed (live)
0
matches in backtest
Dixon-Coles ρ

Model families and weights

familyrolelogit weight
Eloteam strength from results
Poissonscoreline distribution from attack/defence rates
Dixon-Coleslow-score dependency correction (ρ fitted)
Gradient boostingnon-linear features, regularised
Market modelno-vig prices as context only — never in the published probability
Isotonic calibrationmaps ensemble outputs to observed frequencies

Weights come from services/ml/artifacts/weights.json, fitted walk-forward per season. Market weight applies to context_adjusted_1x2 only; the published probability is model-only.

Model changelog

  1. ens_v0.1
    1X2_ensemble · 28/08/2026
    Ensemble of Elo, Poisson, Dixon-Coles (rho fitted per league) and gradient boosting (HistGradientBoosting, median-imputed, regularised). Logit-average with walk-forward weights per season; isotonic calibration on held-out seasons. Market blend reported only as context_adjusted_1x2 — published probability is model-only (spec §31). Signals: adjusted form, league home advantage from history, xG attack/defence ratings where the CSV carries xG (2026/27), draw-risk radar. Known limit: does not yet beat the closing line (backtest log-loss ≈0.99 vs market 0.96–0.98).