Expected goals (xG)
The number of goals an average team would be expected to score from the chances it actually created.
Every shot is assigned a scoring probability based on distance, angle, body part, assist type and defensive pressure. Summing those probabilities across a match gives expected goals, a measure of chance quality rather than finishing luck.
xG is far more stable from match to match than goals themselves, which is why soccer models in EPL and MLS lean on it heavily. A team consistently out-creating opponents while losing on the scoreboard is usually undervalued by the raw table.
The metric describes chance quality, not intent or effort, and it says nothing about a single shot. It becomes reliable across dozens of matches, not within one.
Related terms
See it applied
Every published call on AI4Gameday carries a stated confidence and is graded in public once the game is final.