Enhancing organizational performance through employee training and development using k-means cluster analysis

• Main Authors: Escolar-Jimenez, Caryl Charlene, Matsuzaki, Kichie, Okada, Koji, Gustilo, Reggie C.
• Format: text
• Published: Animo Repository 2019
• Subjects: Employees—Training of; Artificial intelligence; Predictive analytics; Electrical and Computer Engineering
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/1878; https://animorepository.dlsu.edu.ph/context/faculty_research/article/2877/type/native/viewcontent
• Institution: De La Salle University

K-Means clustering algorithm for machine learning enables organizations to be intuitive by making data-driven decisions and by ensuring effective HR policies and different interventions will add value to an organization. Training and development is an essential component for firms where tangible evidences manifest when employees become more engaged, motivated and committed to contribute to the success of organizations. An assessment of an employee KSAOs needs through k-means clustering to make inferences by grouping similar data to discover underlying patterns to determine the actual deficiencies in the Achievement Category, Leadership Category and Behavior Category to minimize or totally eliminate the human errors that occurs during evaluations. A raw data of 100 employees were evaluated and profiled to determine the proper trainings needed by identifying the skill gaps of individuals. This cluster analysis was able to perform distinct classifications to determine changes in employee training needs to provide valuable insights to both HR and organizational decision makers to understand how employee behavior and needs are changing. This allow firms to be in a better position to respond positively and offer appropriate training that addresses individual staff needs by monitoring employee performance and identifying problem areas in a timely and accurate manner as opposed to the traditional training approaches utilized by many firms. This fast and efficient algorithm allows a straightforward and objective talent inventory that will be the basis for future hires, promotion and retraining decisions. © 2019, World Academy of Research in Science and Engineering. All rights reserved.