Récit de la méthodologie

Construisez le mouvement de classement couche par couche

Pick two clubs, choose a result, then walk through the rating update from the simplest Elo version to the full beyondELO match adjustment.

La méthodologie suit le système sélectionné

After every layerArsenal +12.7

62.7% Arsenal / 37.3% Bayern Munich

Équipe à domicileArsenal#1

Classement ELO

Équipe à l’extérieurBayern Munich#2

Classement ELO

Arsenal

2-1

Bayern Munich

Step 1

Start with only the two ratings

The two ELO ratings set the win probability before the result moves points.

R_{n e w} = R_{o l d} + K (W - W_{e})

En savoir plus sur cette étape

Calcul à ce stadeArsenal +9.9

Arsenal50.4%

Bayern Munich49.6%

Arsenal2066 -> 2076+9.9

Bayern Munich2063 -> 2053-9.9

Voici la base avant l’ajout du contexte.

Only the two starting ratings and the chosen result are active here. Every later step changes this same exchange.

Step 2

Add match importance with adaptive K

Competition and round weights replace a single base K.

K_{ba se} = f (co m p e t i t i o n, s t a g e)

En savoir plus sur cette étape

Calcul à ce stadeArsenal +14.9

Arsenal50.4%

Bayern Munich49.6%

Arsenal2066 -> 2081+14.9

Bayern Munich2063 -> 2048-14.9

This layer changes Arsenal by +5.0 Elo compared with the previous step.

Qualifications

Compétition principale

CompétitionsPreliminary1st Round2nd Round3rd RoundQualifying playoff

UCL

UEL

UECL

L’ancien Quatrième Tour utilise la valeur des barrages qualificatifs.

CompétitionsGroup phaseEarly knockoutLate knockout

UCL

UEL

UECL

Step 3

Give the home team its venue edge

Home advantage is added before probability, and removed at neutral venues.

W_{e} = \frac{1}{1 + 1 0 ^{(R_{a w a y} - (R_{h o m e} + H F A)) /400}}

En savoir plus sur cette étape

Calcul à ce stadeArsenal +11.2

Arsenal62.7%

Bayern Munich37.3%

Arsenal2066 -> 2077+11.2

Bayern Munich2063 -> 2052-11.2

This layer changes Arsenal by -3.7 Elo compared with the previous step.

Avantage du terrainTerrain neutre

Step 4

Let the scoreline describe the result

Goal margin scales the move while extra time and penalties soften it.

G = 3 max (1, g o a l ma r g in)

En savoir plus sur cette étape

Calcul à ce stadeArsenal +11.2

Arsenal62.7%

Bayern Munich37.3%

Arsenal2066 -> 2077+11.2

Bayern Munich2063 -> 2052-11.2

This layer changes Arsenal by 0.0 Elo compared with the previous step.

ArsenalBayern Munich

Step 5

Move uncertain teams faster

Own uncertainty speeds movement while opponent uncertainty weakens the evidence.

K_{t e am} = K_{ba se} \times G \times R D_{o w n} \times R e l iabi l i t y (R D_{o pp})

En savoir plus sur cette étape

Calcul à ce stadeArsenal +12.7

Arsenal62.7%

Bayern Munich37.3%

Arsenal2066 -> 2079+12.7

Bayern Munich2063 -> 2050-13.2

This layer changes Arsenal by +1.5 Elo compared with the previous step.

Arsenal uncertaintyBayern Munich uncertainty

Arsenal move x1.15 / x0.99 own uncertainty / opponent reliability

Bayern Munich move x1.19 / x0.99 own uncertainty / opponent reliability

Step 6

Put the full model together

The final exchange combines importance, venue, scoreline, and rating certainty.

R_{n e w} = R_{o l d} + K_{t e am} (W - W_{e})

K_{t e am} = K_{ba se} \times G \times R D_{o w n} \times R e l iabi l i t y (R D_{o pp})

W_{e} = \frac{1}{1 + 1 0 ^{(R_{a w a y} - (R_{h o m e} + H F A)) /400}}

R D_{o w n} = min (3, (\frac{max ( R D , 60 )}{60})^{0.6})

R e l iabi l i t y (R D_{o pp}) = \frac{g ( R D _{o pp} )}{g ( 60 )}, g (R D) = \frac{1}{1 + 3 ( R D /173.7178 ) ^{2} / π ^{2}}

En savoir plus sur cette étape

Chargement du dernier exemple UCL.

Construisez le mouvement de classement couche par couche

Commencez avec deux équipes

Start with only the two ratings

Add match importance with adaptive K

Give the home team its venue edge

Let the scoreline describe the result

Move uncertain teams faster

Put the full model together