Abstract—Employees are one of the most important resources for every company. The company will run well if it has good employees. One way to find out whether the employees’ is worthy of working or not in a company is to conduct an employees’ competency assessment. However, many companies sometimes conduct assessments inappropriately because of the many parameters that need to be considered. For some companies that have thousands of employees, of course, assessing employees’ competence is not an easy thing if it must be done manually. Therefore, this research was made to facilitate the assessment team in assessing employees’ competence by predicting classification using the Naïve Bayes and K-Nearest Neighbor (KNN) algorithms. This research is also expected to help companies analyze employee competence and performance. The dataset used in this research is 3,634 employees’ data with parameters, assessment scores, and learning journey scores. This research will do a comparison to see which model produces better accuracy. The results obtained show that KNN is superior with an accuracy of 99.45% with a comparison of training data and testing data 70:30, 99.33% with a comparison of 75:25, and 99.44% with a comparison of 80:20. While Naïve Bayes obtained an accuracy of 98.44% with a comparison of training data and testing data of 70:30, 98.45% with a comparison of 75:25, and 98.48% with a comparison of 80:20.
 
Keywords—assessment, classification method, employee competencies, Naïve Bayes, K-Nearest Neighbor (KNN)


Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.