Prediction of Employees’ Lateness Determinants using Machine Learning Algorithms

Abstract

© 2020, World Academy of Research in Science and Engineering. All rights reserved. The lateness of employees greatly affects the organization from manpower, to the financial cost, and even to its production. There are a lot of factors which cause the employees to arrive late at work; hence, it is still a hot topic for research. Data mining techniques have good possibilities to address the issue. Through this study, C4.5 and Naïve Bayes, which are both classification algorithms, were used to test in determining the best technique measured by various criteria, which include accuracy, precision, area under the ROC curve (AUC), Recall, and F-Measure. The results of the study were obtained that Naïve Bayes got higher outcomes with 83.3333% accuracy rate compared to C4.5 with 72.2222% and concluded as potential Data Mining Techniques for employees' tardiness. Finally, in this study, the lateness of employees is often done by employees going late to bed.