different parameters are considered but not all of them are mentioned and they don't state how much each one weights in the final figure.
You will not be able to dig deeper into business secrets. Many companies have algorithms that they use everyday on everyone of us, for ads for instance. They analyze
big HUGE data, and their engineers fine tune the analysis and their model. This is pure business gold. Well kept.
In the case of xG, each company defines its own metrics, uses its own data (and/or sometimes public data), and writes its own code/algorithm. It's a secret recipe.
From StatsBomb - What Are Expected Goals (xG)? :
How is xG calculated?
Each xG model has its own characteristics, but these are the main factors that have traditionally been fed into the large majority of Expected Goals models: distance to goal, angle to goal, body part with which the shot was taken, and type of assist or previous action (throughball, cross, set-piece, dribble, etc…). Based on historical information of shots with similar characteristics, the xG model then attributes a value between 0 and 1 to each shot that expresses the probability of it producing a goal.
You can have a look at the way recipes are studied and tested though. Here are some links that explains how it works (better like maths and probability calculus though).
- An Exploration of Expected Goals
- Eindhoven University of Technology -- Expected goals in soccer using predictive analytics
- SKY sports -- Advanced stats explained
- Universidad de Alicante -- An examination of expected goals and shot efficiency in soccer