← All docs

Other

What People Model in Soccer Betting — Targets and Variables Catalog

Summary + sample · full document is 3,555 words

Summary

A cross-cutting synthesis. The other Phase 1 notes are organised by topic area (markets, teams, players, context). This note is organised by prediction target: for each thing a bettor or analyst tries to predict, the standard modelling approach and the variables that feed into it.

Cross-refs: - markets-and-odds.md — full market taxonomy and pricing mechanics. - team-modeling.md — team-strength model families (Dixon-Coles, Elo, Bayesian, ML). - player-quality.md and player-expected-value.md — player ratings and action-value models. - contextual-factors.md — home advantage, fatigu…

Sample

1. Match outcome — 1X2 (home / draw / away)

What's modelled. The discrete distribution P(home_win), P(draw), P(away_win) over 90 minutes (extra time excluded for league/AH conventions).

Standard approaches.

  • Goal-process: independent or bivariate Poisson with Dixon-Coles low-score correction; integrate the score distribution to get 1X2.
  • Latent ratings: Elo / Glicko / SPI mapped through a calibrated logistic to 1X2.
  • Hierarchical Bayesian Poisson (Baio-Blangiardo lineage).
  • Discriminative ML: XGBoost / LightGBM / random forest / MLP with engineered features.
  • Ensembles: weighted blend of a goal-process model and a discriminative model — common in published 2023–25 work (Hubáček-style stacking).

Variables typically used.

Team strength and form

  • Latent attack/defence parameters or Elo rating (current and rolling).
  • Rolling xG-for and xG-against over last N matches (5 / 10 / season).

…

Full document

Pro

Want the full document?

What People Model in Soccer Betting — Targets and Variables Catalog runs 3,555 words. Pro members get every research note in full, plus the arbitrage feed, model outputs, and weekly updates.

Sign in for Pro access →