Who We Are
The minds behind the Soccer Factor Model
Alexandre Andorra
Senior Applied Scientist
Learning Bayesian Statistics
Alex is a data scientist with 8+ years of experience building production probabilistic AI systems. He specializes in Bayesian machine learning, causal inference, and time series forecasting.
He co-founded PyMC Labs, created the Learning Bayesian Statistics podcast (top 1.5% globally with 12,000+ monthly listeners), and founded Intuitive Bayes for online education.
He also worked as a Senior Data Scientist for the Miami Marlins, where he built Bayesian forecasting models processing 50,000+ tracking events per game to inform roster decisions. He holds a US Green Card (EB1) for extraordinary ability in STEM.
Maximilian Göbel
ML Engineer, Lingua Franca Economics
Max is a Machine Learning Engineer and former Post-Doctoral Researcher in Finance/Economics at Universita Bocconi.
Max holds a PhD in Economics from the Lisbon School of Economics & Management. With a background in time series econometrics he specializes in developing statistical models for macroeconomic and financial forecasting.
His work has been published in various academic journals such as the Journal of Econometrics, the Journal of Climate, Energy Economics, and Physica A.
The Soccer Factor Model
The Soccer Factor Model (SFM) was born from a shared passion for football and Bayesian statistics. Inspired by the academic literature on financial asset pricing, the SFM is embedded within a framework to disentangle individual player skill from team performance effects.
The model predicts scoring probabilities for players across Europe's top leagues, while simultaneously quantifying each player's underlying skill. The core methodology is detailed in the research paper Unveiling True Talent: The Soccer Factor Model for Skill Evaluation.