Predicting the Work-Life Balance of Employees Based on the Ensemble Learning Method

Authors : Ayşe Saliha SUNAR, Vedat TÜMEN

Pages : 344-353

Doi:10.17798/bitlisfen.1196174

View : 43 | Download : 37

Publication Date : 2023-06-27

Article Type : Research Paper

Abstract :Work-life has a great impact on other parts of people’s lives. The effort made in the workspace would cause attrition, exhaustion, and health problems. Employers need to take necessary measures to keep employees motivated by helping them balance work and personal lives. Employers could use many different techniques to measure their workers’ work-life balance and analyze them such as questionnaires and machine learning techniques. This research has been carried out to cluster the employees based on the level of attrition using effort and work-life balance parameters. In order to accomplish this, machine learning including ensemble learning techniques is used. An ensemble learning algorithm, random forest, performed almost the same as the support vector machine with the highest score, 95%. Almost all algorithms whether or not they are a member of ensemble learning performed with the f-score of 86%. However, one of the ensemble learning models, xGBoost, performed poorly with the lowest f-score of 69%. All algorithms predicted the lowest and the highest work-life balance scores, however, confused predicting the middle scores insert ignore into journalissuearticles values(class 2 and class 3);.
Keywords : Ensemble Learning, wok life balance, artifical intellegent