Projects

Main Projects

One xG model to rule them all? Challenging the most accurate xG model

A guide on how to train well-performing xG models and how to choose the best xG model for specific use cases.

Robert Bajons, Joint work with Tobias Harringer

rMetrics: A statistically motivated framework for player evaluation using residualized scores

Deriving a unified framework for common metrics in sports analytics.

Robert Bajons, Joint work with Lucas Kook

Expected Pass Value (xPV): A holistic framework for evaluating passing situations in soccer

Using pitch control and pitch value models to evaluate every aspect of passing situations.

Robert Bajons, Joint work with Tobias Harringer

The path to a goal: Understanding possessions via path signatures

Using path signatures and deep learning to gain insights into possession value.

Robert Bajons, Joint work with David Hirnschall

Machine learning based statistical inference in sports analytics

A general framework for valid statistical inference in an interpretable semi-parametric model.

Robert Bajons, Joint work with Lucas Kook

HMMotion: Predicting coverage schemes in the NFL

Using pre-snap tracking data and HMM-model-generated features to predict man vs. zone coverage accurately.

Robert Bajons, Joint work with Rouven Michels and Jan-Ole Koslik

rGAX: Rethinking goals above expectation (GAX)

Deriving a statistically informed alternative to goals over expectation (GAX).

Robert Bajons, Joint work with Lucas Kook

Adaptive generalized logistic lasso (AGLL)

Flexible, robust and fast algorithm for the AGLL with applications to ratings in sports.

Robert Bajons, Joint work with Kurt Hornik

PEP: Evaluating tackles in American football.

Deriving the expected points prevented by a tackle via conditional density estimation of the yards gained by the ball carrier.

Robert Bajons, Joint work with Jan-Ole Koslik, Rouven Michels and Marius Ötting

Predicting the FIFA womens’ world cup 2023

Using hybrid models to develop predictions for the whole 2023 women’s tournament.

Clustering pass rush routes in the NFL

Analysing pass rushs by using a weighted curve clustering apporach.

Robert Bajons, Joint work with Kurt Hornik

Evaluating football (soccer) players

Developing a player rating system using possession sequences derived from event stream data.

Robert Bajons, Joint work with Kurt Hornik