SPORTS BETTING MATH APPLIED PROBABILITY INSTITUTE
ARTÍCULO PILAR

Poisson Goal Expectancy Model

Using the Poisson distribution to predict football match outcomes and odds.

12 min de lectura Avanzado Última actualización 2026-09-20

SBM Stochastic Modeling Lab

Equipo de Modelos de Poisson y Optimización de Bankroll

Laboratorio de investigación enfocado en modelado de distribución de Poisson para goles, optimización de apuestas por el Criterio de Kelly y simulaciones de Monte Carlo para riesgo de ruina.

Bivariate Poisson Match Outcome Modeling Kelly Criterion Geometric Growth Optimization Monte Carlo Risk-of-Ruin Simulation (10M+ Runs)
Usar la Calculadora
Usar la Calculadora →

1. The Poisson Distribution

The Poisson distribution is a discrete probability distribution that expresses the probability of a given number of events occurring in a fixed interval of time or space. The Probability Mass Function (PMF) is:

P(x; λ) = (e^(-λ) * λ^x) / x!

Where λ is the expected number of occurrences, x is the number of occurrences, and e is Euler's number.

2. Modeling Football Goals

Football goals are relatively rare, independent events that occur within a 90-minute timeframe. Empirical evidence shows that goal scoring closely mirrors a Poisson process, making it the industry standard for baseline predictive models.

3. Calculating Expected Goals (λ)

To use Poisson, you need the expected goals (λ) for each team. This is typically derived from:

  • Team Attack Strength
  • Opponent Defense Strength
  • Home Field Advantage

For example, if the home team averages 1.5 goals and the away team defense concedes 10% more than average, λ_home might be 1.65.

4. The 1X2 Probability Model

Assume λ_home = 1.5 and λ_away = 1.2. We calculate the probability of each team scoring 0, 1, 2, 3, etc., goals independently.

For Home scoring 1: P(1; 1.5) = (e^-1.5 * 1.5^1) / 1! = 0.3347

5. Correct Score Matrix

By multiplying the independent probabilities, we form a matrix. For a 1-0 home win:

P(Home=1, Away=0) = P(1; 1.5) * P(0; 1.2) = 0.3347 * 0.3012 = 0.1008

This 10.08% probability is one cell in a 6x6 matrix covering scores from 0-0 to 5-5.

6. Over/Under Markets

To find the probability of Over 2.5 goals, you sum the probabilities of all cells in the matrix where Home Goals + Away Goals > 2 (e.g., 2-1, 1-2, 3-0, 2-2).

7. Both Teams to Score (BTTS)

Tip: For BTTS, calculate 1 - (Probability Home = 0 + Probability Away = 0 - Probability 0-0).

8. Limitations

Basic Poisson assumes goals are independent. In reality, a team losing 1-0 pushes harder, altering scoring rates. It also ignores late-game dynamics and red cards.

9. Dixon-Coles Correction

Introduced in 1997, the Dixon-Coles model corrects the basic Poisson distribution's underestimation of low-scoring draws (0-0, 1-1) by applying an inflation parameter (rho) to specific scorelines.

10. Calculator Tool

Build your own match models with our Poisson Calculator.

Preguntas Frecuentes

AVISO 18+ DE RIESGO