Deep Learning from Spatial Relations for Soccer Pass Prediction

Hubáček, Ondřej; Šourek, Gustav; Železný, Filip

doi:10.1007/978-3-030-17274-9_14

Cited by 13 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows us to compute tailored features influencing the pass difficulty and train supervised machine learning models estimating pass completion probabilities. We build on the features describing passes presented recently (Power et al 2017;Spearman et al 2017;Mchale and Lukasz 2014;Hubáček et al 2018). Table 2 shows an overview of all features we compute for every pass.…”

Section: Pass Probability Estimationmentioning

confidence: 99%

“…Arbués-Sangüesa et al (2020) showed that a player's body orientation (typically not included in off-the-shelf tracking data) has a significant influence on pass completion probabilities as well. Several further extensions, built on top of xPass models, exist in the literature: Fernandez et al (2018) and Spearman et al (2017) include xPass models as central ingredients for computing their expected possession values, and Hubáček et al (2018) use it to try to predict which pass will be played next in any given situation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Expected passes

Anzer

Bauer

2022

Data Min Knowl Disc

View full text Add to dashboard Cite

Passes are by far football’s (soccer) most frequent event, yet surprisingly little meaningful research has been devoted to quantify them. With the increase in availability of so-called positional data, describing the positioning of players and ball at every moment of the game, our work aims to determine the difficulty of every pass by calculating its success probability based on its surrounding circumstances. As most experts will agree, not all passes are of equal difficulty, however, most traditional metrics count them as such. With our work we can quantify how well players can execute passes, assess their risk profile, and even compute completion probabilities for hypothetical passes by combining physical and machine learning models. Our model uses the first 0.4 seconds of a ball trajectory and the movement vectors of all players to predict the intended target of a pass with an accuracy of $$93.0\%$$ 93.0 % for successful and $$72.0\%$$ 72.0 % for unsuccessful passes much higher than any previously published work. Our extreme gradient boosting model can then quantify the likelihood of a successful pass completion towards the identified target with an area under the curve (AUC) of $$93.4\%$$ 93.4 % . Finally, we discuss several potential applications, like player scouting or evaluating pass decisions.

show abstract

Section: Pass Probability Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Expected passes

Anzer

Bauer

2022

Data Min Knowl Disc

View full text Add to dashboard Cite

show abstract

“…Machine Learning, in its definition, is a field in Computer Science that can study certain patterns from data sets and make predictions or classifications based on those data sets. The use of Machine Learning in problems like this is very suitable, because of the large amount of data available, soccer is also difficult to predict based on logic, or other explicit reasons [3]. Some examples of popular Machine Learning algorithms today are Artificial Neural Network (ANN) and Support Vector Machine (SVM).…”

Section: Introductionmentioning

confidence: 99%

implementing the Expected Goal (xG) model to predict scores in soccer matches

Umami

Gautama²,

Hatta

2021

IJIIS : Int. J. Inform. Inform. Systems.

View full text Add to dashboard Cite

Football is a sport that has the most fans in the world. What makes sebak patterns so popular are their uncertain and unpredictable results. There are many factors that affect the outcome of a football match, including strategy, skill, and even luck. Therefore, guessing the results of a soccer match is an interesting problem. All shots are grouped into sections on the playing field and theoretical goal scores are applied to each area. The factors analyzed are: distance of shot from goal and angle of shot in relation to goal. When calculating xG, it is recommended that the distance and angle of the shot are important. The combination of the two xG factors is better calculated than each variable only. In addition, this xG check has been able to relatively accurately identify the mid-table teams that score and concede goals.

show abstract

“…One of the most significant challenges when modeling passes in soccer is that, in practice, passes can go anywhere on the field. Previous attempts on quantifying pass success probability and expected value from passes in both soccer and basketball assume that the passing options a given player has are limited to the number of teammates on the field, and centered at their location at the time of the pass (Power et al 2017;Cervone et al 2016;Hubáček et al 2018). However, in order to accurately estimate the impact of passes in soccer (a key element for estimating the future pathways of a possession), we need to be able to make sense of the spatial and contextual information that influences the selection, accuracy, and potential risk and reward of passing to any other location on the field.…”

Section: Estimating Pass Impact At Every Location On the Fieldmentioning

confidence: 99%

A framework for the fine-grained evaluation of the instantaneous expected value of soccer possessions

2021

View full text Add to dashboard Cite

The expected possession value (EPV) of a soccer possession represents the likelihood of a team scoring or conceding the next goal at any time instance. In this work, we develop a comprehensive analysis framework for the EPV, providing soccer practitioners with the ability to evaluate the impact of observed and potential actions, both visually and analytically. The EPV expression is decomposed into a series of subcomponents that model the influence of passes, ball drives and shot actions on the expected outcome of a possession. We show we can learn from spatiotemporal tracking data and obtain calibrated models for all the components of the EPV. For the components related with passes, we produce visually-interpretable probability surfaces from a series of deep neural network architectures built on top of flexible representations of game states. Additionally, we present a series of novel practical applications providing coaches with an enriched interpretation of specific game situations. This is, to our knowledge, the first EPV approach in soccer that uses this decomposition and incorporates the dynamics of the 22 players and the ball through tracking data.

show abstract

Deep Learning from Spatial Relations for Soccer Pass Prediction

Cited by 13 publications

References 4 publications

Expected passes

Expected passes

implementing the Expected Goal (xG) model to predict scores in soccer matches

A framework for the fine-grained evaluation of the instantaneous expected value of soccer possessions

Contact Info

Product

Resources

About