Clustering Cadet Training Performance Using K-Means and Ward's Method Evidence from OTMon Maritime Monitoring System

Abstract

This study investigates cadet performance segmentation during on-board maritime training using clustering analysis of data from the On Training Monitoring (OTMon) system. Grounded in the competency-based education framework and experiential learning theory, the research aims to identify behavioral patterns and competency levels among 80 maritime cadets over a twelve-month sea-based training program. The OTMon application continuously recorded task completion rates, feedback interactions, sign-on consistency, and report submissions. K-Means clustering and Principal Component Analysis (PCA) revealed three distinct cadet profiles: Cluster 1 (high-performing) with average task completion of 92.4% and feedback frequency of 15.2 times/month; Cluster 2 (administratively consistent) with 88.1% completion but only 6.3 feedback interactions/month; and Cluster 3 (at-risk) with 67.5% completion and 3.8 feedback interactions/month. Linear Discriminant Analysis (LDA) validated the clusters with 98.8% resubstitution accuracy and 97.6% cross-validation accuracy, supported by generalized squared distances above 9.5 between all cluster pairs, indicating strong separation. These findings demonstrate that unsupervised clustering can reliably distinguish high-performing cadets from those needing targeted intervention, enabling data-informed mentoring and adaptive learning strategies in maritime education. The contribution of this study lies in integrating digital monitoring data with both unsupervised and supervised machine learning methods to enhance competency assessment. The novelty is in applying maritime-specific learning analytics for real-time performance segmentation, offering a scalable diagnostic framework for improving supervision quality and supporting individualized cadet development in vocational training contexts.