Data-driven football possession value model (xT/VAEP) to quantify ball progression and player impact.
-
Updated
Mar 17, 2026 - Jupyter Notebook
Data-driven football possession value model (xT/VAEP) to quantify ball progression and player impact.
⚽ 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
Production-grade football analytics API — VAEP, xT, XGBoost predictions, Claude AI scouting reports, WebSocket live updates, 472 tests passing
Maintained fork of socceraction — SPADL event conversion + VAEP action valuation for soccer analytics
Production-grade football intelligence platform — Expected Threat (xT), trained xG model, VAEP-style possession value, pitch control from StatsBomb 360 freeze frames, packing, data-driven player role discovery, AI tactical commentary. Real World Cup 2022 / Premier League data, FastAPI + React.
Probabilistic ML framework for risk-aware soccer action evaluation using xSuccess and adjusted VAEP.
H-VAEP and H-xT: Valuing Offensive On-the-Ball Actions in Handball by Estimating Probabilities
Notebooks developed during the Data Science applied to Soccer at UFMG.
Open-source football analytics pipeline for process-based player valuation using StatsBomb data, VAEP-style scoring, validation, and Streamlit.
To associate your repository with the vaep topic, visit your repo's landing page and select "manage topics."