BasketballTennisRugbyTable tennisMotorsportVolleyballIce hockeyBaseballHandballMMACricketMore football
Football / Methodology
Prediction engine

Methodology

Every prediction starts with expected goals for each team. Those numbers create a scoreline matrix, and the markets on BetSignals are read from that same matrix. This keeps 1X2, totals, BTTS, correct score, and value bets tied to one model.

EngineDixon-Coles bivariate Poisson
Input window365-day league fit, last-15 fallback
Team signalAttack rating, defence rating, Elo, form
Market sourceOne shared scoreline matrix
Refresh cycleHourly cache refresh
Home xG
home attack x away defence x home edge
Away xG
away attack x home defence
Fair odds
1 / model probability

Prediction pipeline

5 steps
1

Set the baseline

We start from league scoring rates so every match begins inside the correct competition context.

2

Rate each team

Attack and defence ratings are fitted from recent matches, weighted so newer games matter more.

3

Adjust the context

Home advantage, form, xG, and thinner data samples are blended without letting one noisy match dominate.

4

Build the score matrix

The model estimates every likely scoreline, then applies Dixon-Coles correction to common low scores.

5

Derive the markets

1X2, over/under, BTTS, correct score, and fair odds are calculated from the same scoreline distribution.

Scoreline matrix

Instead of picking a single result, the model estimates a probability for each scoreline. Markets are then summed from the cells that match that bet type.

Example only. These percentages are illustrative and are not live odds.
0-0
8%
1-0
14%
1-1
13%
2-1
11%
2-0
9%
0-1
10%
2-2
6%
3-1
5%
Other
24%

Fitted ratings

When enough competition data exists, BetSignals fits attack, defence, and home advantage ratings directly from the match history. Recent games are weighted more heavily so ratings can react to changes in team quality.

Fallback mode

If a league or team does not have enough fitted data, the app falls back to recent form, Elo-style strength, xG where available, and conservative league averages. Thin samples are shrunk toward normal scoring rates.

Key parameters

These values describe the current model configuration used by BetSignals.

ParameterValueWhat it means
Modeldixon-coles-v2Bivariate Poisson with Dixon-Coles low-score correction.
Low-score correction-0.13Re-weights 0-0, 1-0, 0-1, and 1-1 outcomes.
Fit window365 daysMatches considered when fitting competition ratings.
Recency half-life90 daysA match weight halves roughly every three months.
Fallback form windowLast 15Per-team fallback when no fitted competition model exists.
xG blend50 / 50Blends expected goals with actual goals when xG is available.
Default home advantagex1.22Used before a competition-specific value is fitted.
Shrinkage prior4 matchesPulls thin samples toward the league average.
Scoreline matrix0-8 goalsJoint distribution is truncated at 8 goals per side.
Rating refreshHourlyFitted ratings are cached and lazily refreshed.