The Model
How ForzaPitch predicts football matches
01 Methodology
ForzaPitch uses a Poisson regression model enhanced with the Dixon-Coles correction to predict football match outcomes.
For each match, we estimate the expected goals (xG) for each team based on their attacking and defensive form,
Elo rating, home advantage, and league-wide scoring averages. The Poisson distribution then gives us the
probability of every possible scoreline, from which we derive 1X2, over/under, and other markets.
02 Elo Ratings
Each team carries a global Elo rating updated after every match. For cup competitions where two teams from
different leagues meet, we use Elo-weighted league baselines to correct for the difference in competitive level.
Weekly accuracy — last 8 weeks
Period average: 60.9%
61.5%
Global Accuracy
Analysed: 2150 matches
Calibration
A well-calibrated model predicts 60% probability events correctly about 60% of the time. The table below compares our predicted confidence bands against actual outcomes.
model
perfect calibration
● <7pp deviation: good / mid / far
| Confidence band | Matches | Expected (mid) | Actual |
|---|---|---|---|
| 50–60% | 785 | 55.0% | 56.4% |
| 60–70% | 818 | 65.0% | 60.3% |
| 70–100% | 547 | 85.0% | 70.7% |