{
  "id": 6654802,
  "title": "Correct score, BTTS and Over/Under probabilities with Dixon-Coles: what I learned building it for MLS and Liga MX",
  "url": "https://urgent.news/2026/09/10/correct-score-btts-and-over-under-probabilities-with-dixon-coles-what",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-09-10T22:25:35.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/commodus67/correct-score-btts-and-overunder-probabilities-with-dixon-coles-what-i-learned-building-it-for-39dc"
  },
  "original_language": "en",
  "account": "The article discusses a model called Dixon-Coles used to predict football match outcomes, including probabilities of win, draw, or loss, Over/Under 2.5 goals, and Both Teams To Score. This model, which builds upon the traditional Poisson distribution approach, addresses its limitations by incorporating a correction factor for low-scoring games. The author tests this Dixon-Coles model across eight less-known football leagues: MLS, Liga MX, Liga de Expansión MX, Brasileirão Série B, USL Championship, Colombia’s Primera A, Uruguay’s Primera División, and Norway’s Eliteserien. The Dixon-Coles correction adjusts the probabilities assigned to specific score outcomes, such as 0-0, 1-1, and 1-0 or 0-1, based on a parameter called ρ (rho), which varies across leagues. The article also explains the methodology for data collection, including data from ESPN’s public scoreboard and adjustments for team age and other factors. The author emphasizes that this model serves as a baseline for comparison with betting prices, providing a quantitative approach to match predictions without incorporating factors like injuries or team news.",
  "summary": "Most football prediction pages give you three numbers — home, draw, away — and no way to check where they came from. I wanted the opposite: one model, fitted on real results, that produces the 1X2 probabilities, the Over/Under 2.5 line, Both Teams To Score and the exact-score grid, all from the same place, so they can't contradict each other. The model I ended up with is Dixon-Coles. This post is…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}