Have a personal or library account? Click to login
Which indicators matter? Using performance indicators to predict in-game success-related events in association football Cover

Which indicators matter? Using performance indicators to predict in-game success-related events in association football

International Journal of Computer Science in Sport
Volume 24 (2025): Issue 2 (June 2025)
By: Steffen Lang,  Thomas Wimmer,  Alexander Erben and  Daniel Link  
Open Access
|Jul 2025

Figures & Tables

Figure 1.

Visualization of the In-Play Prediction Masking approach, the rolling window approach, and the utilized PIs; PGs; IW and PW window sizes. The lower band visualizes the rolling window, whereas all windows moved one step further. In brackets the number of configuration feature levels.
Visualization of the In-Play Prediction Masking approach, the rolling window approach, and the utilized PIs; PGs; IW and PW window sizes. The lower band visualizes the rolling window, whereas all windows moved one step further. In brackets the number of configuration feature levels.

Figure 2.

Pearson’s inter-correlation of PIs and PGs with a window size of 15 minutes ordered for readability. Complete results are shown in Table 3 in the Appendix.
Pearson’s inter-correlation of PIs and PGs with a window size of 15 minutes ordered for readability. Complete results are shown in Table 3 in the Appendix.

Figure 3.

MCC results of all experiments split by MLMs and PGs. Each boxplot contains results of 700 experiments, except for the PGisEntr3rd with 250 experiments. The red dotted line indicates MCC=0.
MCC results of all experiments split by MLMs and PGs. Each boxplot contains results of 700 experiments, except for the PGisEntr3rd with 250 experiments. The red dotted line indicates MCC=0.

Figure 4.

MCC results of all experiments split by PIs. Each boxplot contains the results of 545 experiments. Boxplots are sorted by their MCCmean in descending order. The red dotted line indicates MCC=0.
MCC results of all experiments split by PIs. Each boxplot contains the results of 545 experiments. Boxplots are sorted by their MCCmean in descending order. The red dotted line indicates MCC=0.

Figure 5.

a) Top 3 and b) Bottom 3 PIs for each PG. PIs are sorted by their mean MCC results in descending order. Each boxplot contains the results of 125 experiments, except for the PGisEntr3rd with 45 experiments. The red dotted line indicates MCC=0.
a) Top 3 and b) Bottom 3 PIs for each PG. PIs are sorted by their mean MCC results in descending order. Each boxplot contains the results of 125 experiments, except for the PGisEntr3rd with 45 experiments. The red dotted line indicates MCC=0.

Figure 6.

The percentual appearance in the Top 10% PI-combinations in the application scenario (Part III) of a) the selected Top 10 individual Pls, b) the number of individual Pls combined, and c) the input window length.
The percentual appearance in the Top 10% PI-combinations in the application scenario (Part III) of a) the selected Top 10 individual Pls, b) the number of individual Pls combined, and c) the input window length.

Figure 7.

Application of the trained model (rank 3) for an unseen match between FC Bayern Munich (FCB) vs SC Paderborn (SCP) in Season 19/20 which resulted in a 3:2. In the upper half (FCB) and the lower half (SCP) for each team important events (corner kicks, given cards, goals scored, shots taken), PIDanger and PIEntr3rd, and prediction values are illustrated over the course of the match. Also, Dominance by Link et al. (2016) and the goal prediction difference between both teams, as our proposed match momentum metric, are shown. Additionally, eight important sequences (P1-8) are highlighted.
Application of the trained model (rank 3) for an unseen match between FC Bayern Munich (FCB) vs SC Paderborn (SCP) in Season 19/20 which resulted in a 3:2. In the upper half (FCB) and the lower half (SCP) for each team important events (corner kicks, given cards, goals scored, shots taken), PIDanger and PIEntr3rd, and prediction values are illustrated over the course of the match. Also, Dominance by Link et al. (2016) and the goal prediction difference between both teams, as our proposed match momentum metric, are shown. Additionally, eight important sequences (P1-8) are highlighted.

Figure 8.

Ranking of PIs for PGisEntr3rd. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.
Ranking of PIs for PGisEntr3rd. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.

Figure 9.

Ranking of PIs for PGisEntrBox. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.
Ranking of PIs for PGisEntrBox. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.

Figure 10.

Ranking of PIs for PGisCorner. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.
Ranking of PIs for PGisCorner. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.

Figure 11.

Ranking of PIs for PGisShot. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.
Ranking of PIs for PGisShot. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.

Figure 12.

Ranking of PIs for PGisGoal. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.
Ranking of PIs for PGisGoal. PIs are sorted by their mean MCC results in descending order. The red dotted line indicates MCC=0.

Figure 13.

Application of the 1st ranked model for an unseen match between FC Bayern Munich (FCB) vs SC Paderborn (SCP) in Season 19/20 which resulted in a 3:2. In the upper half (FCB) and the lower half (SCP) for each team important events (corner kicks, given cards, goals scored, shots taken), Dominance by Link et al. (2016) and the prediction difference, as our proposed match momentum metric, are shown.
Application of the 1st ranked model for an unseen match between FC Bayern Munich (FCB) vs SC Paderborn (SCP) in Season 19/20 which resulted in a 3:2. In the upper half (FCB) and the lower half (SCP) for each team important events (corner kicks, given cards, goals scored, shots taken), Dominance by Link et al. (2016) and the prediction difference, as our proposed match momentum metric, are shown.

Figure 14.

Application of the 2nd ranked model for an unseen match between FC Bayern Munich (FCB) vs SC Paderborn (SCP) in Season 19/20 which resulted in a 3:2. In the upper half (FCB) and the lower half (SCP) for each team important events (corner kicks, given cards, goals scored, shots taken), Dominance by Link et al. (2016) and the prediction difference, as our proposed match momentum metric, are shown.
Application of the 2nd ranked model for an unseen match between FC Bayern Munich (FCB) vs SC Paderborn (SCP) in Season 19/20 which resulted in a 3:2. In the upper half (FCB) and the lower half (SCP) for each team important events (corner kicks, given cards, goals scored, shots taken), Dominance by Link et al. (2016) and the prediction difference, as our proposed match momentum metric, are shown.

An overview of the five utilized machine learning models applied with default configurations in the study and the minor individual changes in configuration that were determined as optimal in hyperparameter tuning experiments on subsets of the data_

Machine Learning ModelPython libraryConfigurationURL to documentation
Logistic Regression (LR)Scikit-learn 1.4.0

  • class weights in loss: balanced (inversely proportional weighting according to class frequencies in train set)

  • training metric: binary cross entropy

https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html#sklearn.linear_model.LogisticRegression
Gaussian Naive Bayes (NB)Scikit-learn 1.4.0 https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.GaussianNB.html
Support Vector Machine (SVM)Scikit-learn 1.4.0

  • class weights in loss: balanced

  • training metric: hinge loss

https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html#sklearn.svm.SVC
K-Nearest-Neighbors (KNN)Scikit-learn 1.4.0

  • n_neighbors: 2

  • weights: Euclidean distance

https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html#sklearn.neighbors.KNeighborsClassifier
Neural Network (NN)PyTorch 2.3.0

  • class weights in loss: balanced

  • 4 hidden layers with 256, 512, 128, 16 channels, respectively

  • learning rate: 0.001 with exponential decay

  • optimizer: Adam

  • training until convergence of validation loss (early stopping)

  • dropout probability: 0.4

  • activation function: LeakyReLU (Sigmoid in the last layer)

  • training metric: binary cross entropy

https://pytorch.org/docs/stable/nn.html

a) Performance indicators (PIs) and b) Prediction goals (PGs) of a team and their definitions utilized in our study_ PIs 1–14 as individual PIs and 15–28 as the difference to the opponent team of the individual ones_ The definition of a PI is always based on the performance of the respective team in an interval and is either an event performed, or a metric based on actions of the team_ The definition of a PG is that the event happens at minimum once in the respective prediction window for the team_

NoAbbreviationDefinition
a) Performance Indicators (PI)
1PICornerNumber of corner kicks
2PIEntrBoxNumber of entries of a player with ball possession into the opponent box
3PIEntr3rdNumber of entries of a player with ball possession into the attacking third
4PIGoalNumber of goals scored
5PIShotNumber of shot attempts
6PICrossNumber of crosses
7PITackWonNumber of tacklings won
8PIPassBoxNumber of successful passes in or into the opponent box
9PIPass3rdNumber of successful passes in or into the attacking third
10PIBPTime of ball possession
11PIBPBoxTime of ball possession in the box
12PIBP3rdTime of ball possession in the attacking third
13PIOutpOppNumber of outplayed opponent players by successful passes
14PIDangerGoal scoring probability at each moment (Link et al., 2016)
15-28PIPI_diffDifference of both PI values, (Team – Opponent)
b) Prediction Goals (PG)
1PGisGoalA goal event for the team occurs
2PGisShotA shot event for the team occurs
3PGisCornerA corner kick event for the team occurs
4PGisEntrBoxAn entry into the opponent box performed by the team occurs
5PGisEntr3rdAn entry into the attacking third performed by the team occurs

Pearson’s inter-correlation results of PIs and PGs for the window length of 15 minutes_ Top 3 (green) and Bottom 3 (red) PIs per PG are highlighted_ The best and worst results per PG are bold_

PGisGoalPGisCornerPGisShotPGisEntrBoxPGisEntr3rd
PIBP_diff.048.225.333.443.573
PIBP.053.201.319.414.535
PIPass3rd_diff.127.216.340.403.529
PIPass3rd.130.219.312.371.473
PIOutpOpp_diff.114.198.342.419.522
PIOutpOpp.092.207.292.400.486
PIBP3rd_diff.118.201.355.398.507
PIBP3rd.109.227.333.391.468
PIEntr3rd_diff.107.197.343.391.505
PIEntr3rd.089.227.331.401.503
PIDanger_diff.125.190.319.380.481
PIDanger.124.207.303.387.459
PICross_diff.104.190.251.324.387
PICross.106.204.242.323.343
PIEntrBox_diff.106.166.255.312.368
PIEntrBox.077.191.228.324.336
PIShot_diff.071.112.183.286.322
PIShot.057.104.136.227.258
PIBPBox_diff.092.130.199.218.276
PIBPBox.036.133.140.224.222
PICorner_diff.069.083.142.205.253
PICorner.062.124.130.196.213
PIPassBox_diff.058.111.125.164.220
PIPassBox.057.078.086.145.186
PITackWon_diff.052.074.058.138.087
PITackWon.012.157.060.162.138
PIGoal_diff.038−.054−.043−.022−.099
PIGoal−.022−.075−.052−.028−.087
DOI: https://doi.org/10.2478/ijcss-2025-0011 | Journal eISSN: 1684-4769
Journal RSS Feed
Language: English
Page range: 16 - 44
Published on: Jul 31, 2025
Published by: International Association of Computer Science in Sport
In partnership with: Paradigm Publishing Services
Publication frequency: 2 issues per year
Keywords:
Football,
Machine Learning,
In-Play Prediction,
Match Momentum,
Performance Indicators
Related subjects:
Computer sciences,
Databases and data mining,
Computer sciences, other,
Sports and recreation,
Physical education,
Sports and recreation, other

© 2025 Steffen Lang, Thomas Wimmer, Alexander Erben, Daniel Link, published by International Association of Computer Science in Sport
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Previous articleVolume 24 (2025): Issue 2 (June 2025)Next article