Modelling and Analyzing the Employees’ Engagement in Workplace using Machine learning Tools
Mahassine Bekkari1, Abdellah El Fallahi2

1Mahassine BEKKARI*, Logistique, Abdelmalek Essaadi University, Tetuan, Morroco.
2Abdellah EL FALLAHI, Logistique, Abdelmalek Essaadi University, Tetuan, Morroco. 

Manuscript received on March 23, 2021. | Revised Manuscript received on March 27, 2021. | Manuscript published on March 30, 2021. | PP: 243-249 | Volume-9 Issue-6, March 2021. | Retrieval Number: 100.1/ijrte.F5582039621 | DOI: 10.35940/ijrte.F5582.039621
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: In a new economy where immaterial capital is crucial, companies are increasingly aware of the necessity to efficiently manage human capital by optimizing its engagement in the workplace. The accession of the human capital through its engagement is an efficient leverage that leads to a real improvement of the companies’ performance. Despite the staple attention towards human resource management, and the efforts undertaken to satisfy and motivate the personnel, the issue of engagement still persists. The main objective of this paper is to study and model the relation between eight predictors and a response variable given by the employees’ engagement. We have used different models to figure out the relation between the predictors and the dependent variable after carrying out a survey of several employees from different companies. The techniques used in this paper are linear regression, ordinal logistic regression, Gradient Boosting Machine learning and neural networks. The data used in this study is the results of a questionnaire completed by 60 individuals. The results obtained show that the neural networks perform slightly the rest of models considering the training and validation error of modelling and also highlight the complex relation linking the predictors and the predicted. 
Keywords: Human resources management, machine learning; Neural networks, Boosting machine learning, logistic regression.