StatsBomb 360° data from Euro 2024 made easily accessible for analysis

A football Expected Goals (xG) prediction model leveraging advanced machine learning techniques.

Building xG and xGOT based on Statsbomb World Cup 2022 Open Data

⚽️ Unveiling the FIFA World Cup 2022 Final! 🏆 Explore the epic clash between Argentina and France through data-driven visualizations. From shot maps to passing networks and heatmaps, this project combines football excitement with advanced analytics to reveal tactical insights and key moments from one of the greatest matches in history!

Network visualization tool for analyzing passing patterns and player interactions over the course of an entire soccer season using Statsbomb event data.

The Project develops a machine learning model using XGBoost to predict injury risks in women’s football by analyzing workload, recovery metrics, and player data. It identifies key risk factors such as training intensity and workload-recovery balance to provide actionable insights for coaches, reducing injury rates through personalized management.

An interactive web app built with Python & Streamlit to visualize football passing networks from StatsBomb open data. The tool uses Matplotlib/mplsoccer to plot player positions and pass connections on a pitch.

An interactive dashboard for visualizing and analyzing sports statistics, featuring dynamic data visualization

Repository for Parma Calcio Data Scientist assignment. Includes two tasks: building an xG model using StatsBomb open data (event data / freeze-frame) and predicting the 2015/16 Ballon d’Or winner from Big-5 leagues data. Implemented in Python with notebooks and reusable modules.

RAG-Challenge for Football Analysis using Azure OpenAI