Extended xThreat: an explainable quality assessment method for actions in football using game context

K.W. van Arem; Mirjam Bruinsma

doi:10.17028/RD.LBORO.27045427.V1

Abstract

In the last decade, systematic collection of data is increasingly being used in the world of football which enables the use of mathematics to improve the performance of individual players and teams. The choice for either a xThreat model or a VAEP-like model gives a trade-off between explainability and the ability to take in-game context into account. The main goal of this paper is to create an extended xThreat (expected threat) model that can include game context, thus aiming for explainability while taking into account contextual variables.

Original language	English
Pages	135-136
Number of pages	2
DOIs	https://doi.org/10.17028/RD.LBORO.27045427.V1
Publication status	Published - 2024
Event	15th International Conference on the Engineering of Sport: Engineering of Sports 15 - Loughborough University, Loughborough, United Kingdom Duration: 8 Jul 2024 → 10 Jul 2024 https://www.lboro.ac.uk/research/sti-isea-2024/

Conference

Conference	15th International Conference on the Engineering of Sport
Abbreviated title	ISEA 2024
Country/Territory	United Kingdom
City	Loughborough
Period	8/07/24 → 10/07/24
Internet address	https://www.lboro.ac.uk/research/sti-isea-2024/

Keywords

Football analytics
xThreat
Extended xThreat
Player quality
Football
Soccer
Markov chain
Player scouting
Action quality
Expected Threat

Access to Document

10.17028/RD.LBORO.27045427.V1Licence: Unspecified

ISEA_2024_paper_98Final published version, 1.27 MBLicence: CC BY

Cite this

@conference{7a70ffb8ee4042bc9f12044149ee7953,

title = "Extended xThreat: an explainable quality assessment method for actions in football using game context",

abstract = "In the last decade, systematic collection of data is increasingly being used in the world of football which enables the use of mathematics to improve the performance of individual players and teams. The choice for either a xThreat model or a VAEP-like model gives a trade-off between explainability and the ability to take in-game context into account. The main goal of this paper is to create an extended xThreat (expected threat) model that can include game context, thus aiming for explainability while taking into account contextual variables.",

keywords = "Football analytics, xThreat, Extended xThreat, Player quality, Football, Soccer, Markov chain, Player scouting, Action quality, Expected Threat",

author = "{van Arem}, K.W. and Mirjam Bruinsma",

year = "2024",

doi = "10.17028/RD.LBORO.27045427.V1",

language = "English",

pages = "135--136",

note = "15th International Conference on the Engineering of Sport : Engineering of Sports 15, ISEA 2024 ; Conference date: 08-07-2024 Through 10-07-2024",

url = "https://www.lboro.ac.uk/research/sti-isea-2024/",

}

TY - CONF

T1 - Extended xThreat: an explainable quality assessment method for actions in football using game context

AU - van Arem, K.W.

AU - Bruinsma, Mirjam

PY - 2024

Y1 - 2024

N2 - In the last decade, systematic collection of data is increasingly being used in the world of football which enables the use of mathematics to improve the performance of individual players and teams. The choice for either a xThreat model or a VAEP-like model gives a trade-off between explainability and the ability to take in-game context into account. The main goal of this paper is to create an extended xThreat (expected threat) model that can include game context, thus aiming for explainability while taking into account contextual variables.

AB - In the last decade, systematic collection of data is increasingly being used in the world of football which enables the use of mathematics to improve the performance of individual players and teams. The choice for either a xThreat model or a VAEP-like model gives a trade-off between explainability and the ability to take in-game context into account. The main goal of this paper is to create an extended xThreat (expected threat) model that can include game context, thus aiming for explainability while taking into account contextual variables.

KW - Football analytics

KW - xThreat

KW - Extended xThreat

KW - Player quality

KW - Football

KW - Soccer

KW - Markov chain

KW - Player scouting

KW - Action quality

KW - Expected Threat

UR - https://repository.lboro.ac.uk/articles/conference_contribution/Extended_xThreat_an_explainable_quality_assessment_method_for_actions_in_football_using_game_context/27045427/1?file=49243477

U2 - 10.17028/RD.LBORO.27045427.V1

DO - 10.17028/RD.LBORO.27045427.V1

M3 - Abstract

SP - 135

EP - 136

T2 - 15th International Conference on the Engineering of Sport

Y2 - 8 July 2024 through 10 July 2024

ER -