Navigation überspringen
Universitätsbibliothek Heidelberg
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Jayme, Alejandra [VerfasserIn]   i
 Lösel, Philipp [VerfasserIn]   i
 Fischer, Joachim E. [VerfasserIn]   i
 Heuveline, Vincent [VerfasserIn]   i
Titel:Comparison of machine learning methods for predicting employee absences
Verf.angabe:Alejandra Jayme, Philipp D. Lösel, Joachim Fischer, Vincent Heuveline
Verlagsort:Heidelberg
Verlag:Universiätsbibliothek
E-Jahr:2021
Jahr:May 3, 2021
Umfang:1 Online-Ressource (21 Seiten)
Gesamttitel/Reihe:Preprint series of the Engineering Mathematics and Computing Lab (EMCL) ; Preprint no. 2021-02
Fussnoten:Gesehen am 09.03.2023
Abstract:Employee absences cannot be avoided but excessive and uncontrolled absences affect not only the companies and employees but also impact the economy, government and society. Though actual losses are hard to compute, absenteeism has been estimated to cost billions in direct and indirect costs. Addressing employee absences is difficult because the underlying reasons and causes are complex and not straightforward. Compounding this, companies do not have tools to analyze and predict the future risk of employee absences, relying instead on retrospective data that may not be relevant to the current situation at hand. In this study, we show how machine learning methods can be used to predict employee absence risks. Results show that Neural Networks give best accuracy (77%) over Random Forest (72%) and Support Vector Machines (62%). The effect of training data size and varied feature sets on the models’ performances were also tested. Also, a method allowing for ranking the sensitivity of a Neural Network to each feature is presented.
DOI:doi:10.11588/emclpp.2021.02.81078
URL:kostenfrei: Volltext: https://doi.org/10.11588/emclpp.2021.02.81078
 kostenfrei: Volltext: https://journals.ub.uni-heidelberg.de/index.php/emcl-pp/article/view/81078
 DOI: https://doi.org/10.11588/emclpp.2021.02.81078
Datenträger:Online-Ressource
Sprache:eng
K10plus-PPN:1838770240
Verknüpfungen:→ Übergeordnete Aufnahme
 
 
Lokale URL UB: Zum Volltext

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/69050211   QR-Code
zum Seitenanfang