expected-goals

📊⚽ A collection of football analytics projects, data, and analysis by Edd Webster (@eddwebster), including a curated list of publicly available resources published by the football analytics community.

Exploring football and other sports through data. Includes analyses of match events, player performance, xG models, tactical visualizations, and predictive insights.

Machine Learning models to predict goals in football games.

An NHL expected goals (xG) model built with light gradient boosting.

Using wyscout data to create a xG model

Fun with Rocket League tracking data

FBref player stats scraper

An expected goals (xG) model for the AHL. Also applicable to the CHL.

We will analyze in our code the expected goal locations of football players based on which areas of the field, at what times, with which feet, using which parts of their bodies, and from which angles and distances they are most likely to score.

Pipeline that ingests football match/event data from the InStat API into PostgreSQL and trains a RandomForest expected-goals (xG) model.

This repository consists the supplemental materials of the paper "Decomposition of Expected Goal Models: Aggregated SHAP Values for Analyzing Scoring Potential of Player/Team".

An Expected Goals (xG) model built with StatsBomb open data. The project covers data scraping, cleaning, feature engineering, model training, and evaluation to estimate goal probabilities from shot events.

⚽ Système d'analyse de matchs de football en Python (POO) — Calcule VAEP, xG, xT à partir de données réelles StatsBomb (FUS Rabat vs FAR). Héritage · Polymorphisme · Encapsulation

MIT Sloan Sports Analytics Conference 2026 - RIVAL Score: Benchmarking Using Relative Individual Value Assessment

Sistema de scouting de futbolistas basado en datos: clustering de estilos de juego (PCA + K-Means) y predicción de revalorización de mercado (XGBoost) sobre eventos Wyscout.

28 free Claude Code skills for NHL analytics, betting models, and hockey research. Works with PuckAPI MCP server for live data.

Football (soccer) xG model comparison and learning project using StatsBomb open data.

Football analytics: predicting Serie A 2015/16 full-time results from first-half statistics using StatsBomb event data. Includes advanced metrics (xG, PPDA, Field Tilt) and ML classification (SVM, Decision Tree, Naive Bayes).

This repository contains a project developed in R aimed at creating a new model for evaluating Expected Goals (xG) in football.

A structured knowledge hub explaining football statistics, performance metrics, match data, and analytical concepts.