Revisiting Expected Possession Value in Football: Introducing a U-Net Architecture, Reward and Risk for Passes, and a Benchmark

Thijs Overmeer, Thijs Overmeer, Tim Janssen, Wim Nuijten, Wim Nuijten

2025

Abstract

This paper presents an Expected Possession Value (EPV) model for football with three main new components: a U-Net-inspired convolutional neural network architecture, ball height as a feature, and a dual-component pass value model that analyzes reward and risk. We furthermore introduce the Overmeer–Janssen–Nuijten Pass Expected Possession Value benchmark (OJN-Pass-EPV benchmark), which enables a quantitative evaluation of EPV models by using pairs of game states with given relative EPVs. The presented EPV model achieves good results in model loss and Expected Calibration Error on a dataset containing Dutch Eredivisie and 2022 FIFA Men’s World Cup matches and correctly identifies the higher value state in 78% of the game state pairs in the OJN-Pass-EPV benchmark, demonstrating its ability to accurately assess goal-scoring potential. Our findings enable more precise EPV estimations, support risk-reward analysis for passing decisions, and establish quality control standards for EPV models.

Paper Citation

in Harvard Style

Overmeer T., Janssen T. and Nuijten W. (2025). Revisiting Expected Possession Value in Football: Introducing a U-Net Architecture, Reward and Risk for Passes, and a Benchmark. In Proceedings of the 13th International Conference on Sport Sciences Research and Technology Support - Volume 1: icSPORTS; ISBN 978-989-758-771-9, SciTePress, pages 100-109. DOI: 10.5220/0013784300003988

in Bibtex Style

@conference{icsports25,
author={Thijs Overmeer and Tim Janssen and Wim Nuijten},
title={Revisiting Expected Possession Value in Football: Introducing a U-Net Architecture, Reward and Risk for Passes, and a Benchmark},
booktitle={Proceedings of the 13th International Conference on Sport Sciences Research and Technology Support - Volume 1: icSPORTS},
year={2025},
pages={100-109},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013784300003988},
isbn={978-989-758-771-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Sport Sciences Research and Technology Support - Volume 1: icSPORTS
TI - Revisiting Expected Possession Value in Football: Introducing a U-Net Architecture, Reward and Risk for Passes, and a Benchmark
SN - 978-989-758-771-9
AU - Overmeer T.
AU - Janssen T.
AU - Nuijten W.
PY - 2025
SP - 100
EP - 109
DO - 10.5220/0013784300003988
PB - SciTePress