EdgeworthArena
Live dataSign in
Quant Library · Match pricing · Football

Coherent Book Builder

Every market on the board from one distribution, so no two prices can contradict each other.

Match odds, totals, Asian handicaps, both teams to score, correct score and clean sheets, each a sum over the same scoreline grid, with a margin applied at the end rather than market by market.

Inputs

What it takes

3
NameTypeUnitsWhere it comes from
score_matrixn x n arrayprobabilitythe Match Price Engine, or any scoreline model you already own
margin optionalfloatfractionyour book's overround target
lines optionallistgoals or goal differencethe handicap and total lines you quote
Outputs

What it gives back

3
NameTypeUnitsNotes
marketsdict of market -> probability and fair priceprobability, decimal odds
quoteddict of market -> price with the margin ondecimal odds
skellam_checkfloatprobabilitythe largest disagreement between the grid and the exact goal-difference law
Method

How it works

  1. Sum the cells that satisfy each market's condition: x > y for the home win, x + y ≥ 3 for over 2.5, x − y > 1 for a one-goal handicap, and so on.
  2. 3 further steps in the licensed specification
Assumptions
  • The scoreline grid is the whole truth about the match: everything quoted is a function of it.
Limits
  • Markets that are not functions of the final score, such as cards or corners, are outside it.
  • 1 further limits in the licensed specification
Validation

What it was measured at

ok

Computed now, from the same grid the Arena prices with.

Markets from one grid11match odds, totals, handicaps, both teams to score, correct score
Grid against the exact Skellam law1.2e-02largest disagreement over the goal difference
Sum of the whole grid1.000000after truncation at ten goals a side
Over 2.5 at these rates50.6%one sum among many
In the package
  • The full specification: inputs, method, assumptions and limits
  • The validation panel as measured on the day of purchase
  • A reference implementation extracted from the running source
  • Perpetual commercial use for one entity

Reference modules:

  • 2 module(s), named in the licensed specification and shipped in the package
Read this before you buy. The platform's own walk-forward tests say the closing line forecasts football better than these models do. What they give you is a coherent price for every market and match, before the market opens, with the band and the working attached. Any model here that has been beaten by something simpler says so in its limits, and the validation panel above is generated from the platform's result files rather than typed in.