A Goal Scoring Probability Model for Shots Based on Synchronized Positional and Event Data in Football (Soccer)

Bibliographic Data

ID5284696
AuthorsGabriel Anzer (0000-0003-3129-8359), Pascal Bauer (0000-0001-8613-6635)
Year2021
Volume3
Pages624475-624475
Publication date2021-03-29
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueFrontiers in Sports and Active Living (JOURNAL)
Journal identifiersISSN: 2624-9367 • E-ISSN: 2624-9367
PublisherFrontiers Media SA (PUBLISHER • CH)
DOI10.3389/fspor.2021.624475
PMID33889843
OpenAlexW3147122783
LanguageEN
Citations received8
References cited29

Due to the low scoring nature of football (soccer), shots are often used as a proxy to evaluate team and player performances. However, not all shots are created equally and their quality differs significantly depending on the situation. The aim of this study is to objectively quantify the quality of any given shot by introducing a so-called expected goals (xG) model. This model is validated statistically and with professional match analysts. The best performing model uses an extreme gradient boosting algorithm and is based on hand-crafted features from synchronized positional and event data of 105, 627 shots in the German Bundesliga. With a ranked probability score (RPS) of 0.197, it is more accurate than any previously published expected goals model. This approach allows us to assess team and player performances far more accurately than is possible with traditional metrics by focusing on process rather than results

Boosting (machine learning · Data mining · Event (particle physics · Event data · Football · Football team · Geography · Machine learning · Process (computing · Proxy (statistics · Quality (philosophy · Computer Science · Sports Analytics and Performance · Sports Dynamics and Biomechanics · Sports Performance and Training · Artificial Intelligence

Tools

Open DOIOpen Access