Predicting the future performance of soccer players

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Predicting the future performance of soccer players. / Arndt, Cornelius; Brefeld, Ulf.
In: Statistical Analysis and Data Mining, Vol. 9, No. 5, 01.10.2016, p. 373-382.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{fe71904951b5445db7e91a2df5d7812f,
title = "Predicting the future performance of soccer players",
abstract = "We propose a multitask, regression-based approach for predicting future performances of soccer players. The multitask approach allows us to simultaneously learn individual player models as offsets to a general model. We devise multitask variants of ridge regression and ε-support vector regression. Together with a hashed joint feature space, the generalized models can be optimized using standard techniques. Relevant features for the prediction are identified by a modified recursive feature elimination strategy. We report on extensive empirical results using real data from the German Bundesliga.",
keywords = "feature selection, machine learning, multitask regression, predictive analytics, ridge regression, support vector regression, Engineering",
author = "Cornelius Arndt and Ulf Brefeld",
year = "2016",
month = oct,
day = "1",
doi = "10.1002/sam.11321",
language = "English",
volume = "9",
pages = "373--382",
journal = "Statistical Analysis and Data Mining",
issn = "1932-1864",
publisher = "John Wiley & Sons Inc.",
number = "5",

}

RIS

TY - JOUR

T1 - Predicting the future performance of soccer players

AU - Arndt, Cornelius

AU - Brefeld, Ulf

PY - 2016/10/1

Y1 - 2016/10/1

N2 - We propose a multitask, regression-based approach for predicting future performances of soccer players. The multitask approach allows us to simultaneously learn individual player models as offsets to a general model. We devise multitask variants of ridge regression and ε-support vector regression. Together with a hashed joint feature space, the generalized models can be optimized using standard techniques. Relevant features for the prediction are identified by a modified recursive feature elimination strategy. We report on extensive empirical results using real data from the German Bundesliga.

AB - We propose a multitask, regression-based approach for predicting future performances of soccer players. The multitask approach allows us to simultaneously learn individual player models as offsets to a general model. We devise multitask variants of ridge regression and ε-support vector regression. Together with a hashed joint feature space, the generalized models can be optimized using standard techniques. Relevant features for the prediction are identified by a modified recursive feature elimination strategy. We report on extensive empirical results using real data from the German Bundesliga.

KW - feature selection

KW - machine learning

KW - multitask regression

KW - predictive analytics

KW - ridge regression

KW - support vector regression

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=84988431971&partnerID=8YFLogxK

U2 - 10.1002/sam.11321

DO - 10.1002/sam.11321

M3 - Journal articles

AN - SCOPUS:84988431971

VL - 9

SP - 373

EP - 382

JO - Statistical Analysis and Data Mining

JF - Statistical Analysis and Data Mining

SN - 1932-1864

IS - 5

ER -

DOI

Recently viewed

Activities

  1. sneep Frühjahrstagung 2017
  2. JMS Conference: Repurposing Management for the Public Good: Processes, Obstacles and Unintended Consequences
  3. Right-wing spaces. The transnational dimensions of right-wing extremism
  4. Organizing ‘Safe Spaces’ for Creative Collaboration
  5. Digital Capitalism meets “Leberkaspepi”: Temporal Orientations in Business Models as a Source of Platform Power in Mature Industries
  6. Keynote: Routines Research: More Critical?
  7. LABOR.A® 2019 - LABORA19
  8. Eliciting energization by mentally contrasting future and reality
  9. Look Who's Talking How - A Teaching Intervention on Gender-Sensitive Language in Higher Education
  10. Lebensband Elbe
  11. Reviewer in recruitment commission for external university
  12. 39th EGOS Colloquium - EGOS 2023
  13. Zeitschrift für Personalforschung (Zeitschrift)
  14. Leuphana Universität Lüneburg (Organisation)
  15. Graduate School (Organisation)
  16. Idea Greenhouses are made of glass. Tensions in experimental spaces for creative collaboration in front-end pharmaceutical research
  17. Strategic Management Society 36th Annual Conference 2016
  18. Fakultät Management und Technologie (Organisation)
  19. Digital Capitalism without Firms? Consequences for the Organization and Regulation of Work from an Employment Systems Perspective
  20. Introducción a la Gestión Cultural
  21. „Plattformbasiertes Arbeiten“, Titel Vortrag: Partizipation von CrowdworkerInnen auf Crowdsourcing-Plattformen
  22. 4. Doktoranden-Workshop des Netzwerks Norddeutsche Demokratieforschung - 2011
  23. 10th Austrian Early Scholars Workshop in Management (AESW)
  24. Workshop at the Université Paris-Dauphine - PEER 2011
  25. 4th Annual Meeting of the Society For Business Ethics - SBE 2015
  26. Organization Studies (Fachzeitschrift)
  27. Leuphana Concert Lab
  28. Mentor for Lukas Vogelgsang
  29. VHB ProDok Seminar "Advanced Topics in Organization Theory"
  30. Green Startups 2015
  31. Geben Plattformen CrowdworkerInnen eine Stimme? Eine explorative Studie zur CrowdworkerInnen-Partizipation auf Crowdsourcing-Plattformen
  32. Reviewer in recruitment commission for external university
  33. Meta (Zeitschrift)
  34. Bildung für eine nachhaltige Entwicklung in Lateinamerika
  35. Leuphana Universität Lüneburg (Organisation)
  36. Praktiker Panel-Diskussion: How organizations change successfully: Sustainabile and Digital Transformation
  37. Work and Organizational Psychology Conference
  38. Emerging Entrepreneurship – From Idea to Opportunity − Comparative Study in France, Germany and Sweden