Multi-Output Regression for the Prediction of World-Class Performances in Women’s Handball

The purpose of this study was to investigate the relationship between workload and in-game technical and athletic performance. To achieve this,A modeling approach that predicts multiple numerical output variables simultaneously, particularly useful when these outputs are correlated (multi-output reg...

Full description

Saved in:
Bibliographic Details
Main Authors: Rayane Elimam, Nicolas NICOLAS, Jacques Prioux, Jacky Montmain, Stephane Perrey
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10972112/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849322854409043968
author Rayane Elimam
Nicolas NICOLAS
Jacques Prioux
Jacky Montmain
Stephane Perrey
author_facet Rayane Elimam
Nicolas NICOLAS
Jacques Prioux
Jacky Montmain
Stephane Perrey
author_sort Rayane Elimam
collection DOAJ
description The purpose of this study was to investigate the relationship between workload and in-game technical and athletic performance. To achieve this,A modeling approach that predicts multiple numerical output variables simultaneously, particularly useful when these outputs are correlated (multi-output regression) models were used to predict 7 performance indicators based on previous training and game athletic workloads measured by Inertial Measurement Units (IMU) indicators, previous in-game actions annotated by staff members and game contextual factors. We compared 4 single-output models (kNN, regression tree, random forest and(NN) Predictive models inspired by the human brain, used in this study for multi-output prediction in sports performance analysis (neural networks)), their multi-output counterparts and aA baseline model predicting future performance as the average of each player’s past performance, serving as a simple reference for comparison with more complex models (dummy baseline) (predicting the average performance of each player over the last month) in terms of average(Root Mean Squared Error) A measure of the quadratic difference between predicted and actual values in regression models (RMSE) (aRMSE) during aAn evaluation method where past training and game data are used sequentially to predict performance of the next game (chronological evaluation) where previous trainings and games data are used to train models to predict the next game performances. Overall, the use of multi-output regression models enabled a decrease of the average predictive error (A metric for prediction error that evaluates model accuracy in terms of average squared errors across multiple outputs in a multi-output models (aRMSE) = 4.23) in regards to their single-output counterparts (aRMSE = 4.35) while providing a significant decrease of average computation times (4.75 to 0.82 seconds). Among the 4 multi-output models, only the kNN (aRMSE = 3.852) and random forest (aRMSE = 3.888) performed better than the dummy regressor (aRMSE = 3.944). These results point towards that physical training may have a limited impact on game performance.
format Article
id doaj-art-9710a9e8d10a409daeb599caeee31312
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-9710a9e8d10a409daeb599caeee313122025-08-20T03:49:13ZengIEEEIEEE Access2169-35362025-01-0113698736988710.1109/ACCESS.2025.356083810972112Multi-Output Regression for the Prediction of World-Class Performances in Women’s HandballRayane Elimam0Nicolas NICOLAS1https://orcid.org/0000-0002-3065-0712Jacques Prioux2Jacky Montmain3Stephane Perrey4https://orcid.org/0000-0002-8741-629XEuroMov Digital Health in Motion, University of Montpellier, IMT Mines Alès, Montpellier, FranceEuroMov Digital Health in Motion, University of Montpellier, IMT Mines Alès, Montpellier, FranceMovement, Sport, Health Laboratory, Université Rennes 2, Rennes, Bruz, FranceEuroMov Digital Health in Motion, University of Montpellier, IMT Mines Alès, Montpellier, FranceEuroMov Digital Health in Motion, University of Montpellier, IMT Mines Alès, Montpellier, FranceThe purpose of this study was to investigate the relationship between workload and in-game technical and athletic performance. To achieve this,A modeling approach that predicts multiple numerical output variables simultaneously, particularly useful when these outputs are correlated (multi-output regression) models were used to predict 7 performance indicators based on previous training and game athletic workloads measured by Inertial Measurement Units (IMU) indicators, previous in-game actions annotated by staff members and game contextual factors. We compared 4 single-output models (kNN, regression tree, random forest and(NN) Predictive models inspired by the human brain, used in this study for multi-output prediction in sports performance analysis (neural networks)), their multi-output counterparts and aA baseline model predicting future performance as the average of each player’s past performance, serving as a simple reference for comparison with more complex models (dummy baseline) (predicting the average performance of each player over the last month) in terms of average(Root Mean Squared Error) A measure of the quadratic difference between predicted and actual values in regression models (RMSE) (aRMSE) during aAn evaluation method where past training and game data are used sequentially to predict performance of the next game (chronological evaluation) where previous trainings and games data are used to train models to predict the next game performances. Overall, the use of multi-output regression models enabled a decrease of the average predictive error (A metric for prediction error that evaluates model accuracy in terms of average squared errors across multiple outputs in a multi-output models (aRMSE) = 4.23) in regards to their single-output counterparts (aRMSE = 4.35) while providing a significant decrease of average computation times (4.75 to 0.82 seconds). Among the 4 multi-output models, only the kNN (aRMSE = 3.852) and random forest (aRMSE = 3.888) performed better than the dummy regressor (aRMSE = 3.944). These results point towards that physical training may have a limited impact on game performance.https://ieeexplore.ieee.org/document/10972112/Team sportsworkloadssport analyticsin-game performancesupervised learning
spellingShingle Rayane Elimam
Nicolas NICOLAS
Jacques Prioux
Jacky Montmain
Stephane Perrey
Multi-Output Regression for the Prediction of World-Class Performances in Women’s Handball
IEEE Access
Team sports
workloads
sport analytics
in-game performance
supervised learning
title Multi-Output Regression for the Prediction of World-Class Performances in Women’s Handball
title_full Multi-Output Regression for the Prediction of World-Class Performances in Women’s Handball
title_fullStr Multi-Output Regression for the Prediction of World-Class Performances in Women’s Handball
title_full_unstemmed Multi-Output Regression for the Prediction of World-Class Performances in Women’s Handball
title_short Multi-Output Regression for the Prediction of World-Class Performances in Women’s Handball
title_sort multi output regression for the prediction of world class performances in women x2019 s handball
topic Team sports
workloads
sport analytics
in-game performance
supervised learning
url https://ieeexplore.ieee.org/document/10972112/
work_keys_str_mv AT rayaneelimam multioutputregressionforthepredictionofworldclassperformancesinwomenx2019shandball
AT nicolasnicolas multioutputregressionforthepredictionofworldclassperformancesinwomenx2019shandball
AT jacquesprioux multioutputregressionforthepredictionofworldclassperformancesinwomenx2019shandball
AT jackymontmain multioutputregressionforthepredictionofworldclassperformancesinwomenx2019shandball
AT stephaneperrey multioutputregressionforthepredictionofworldclassperformancesinwomenx2019shandball