A Data-Driven Framework for Tailoring Project Management Education to Individual Needs Using Machine Learning

Project management education plays a key role in developing project professionals, as it is understood as a complex competence integrating contextual, interpersonal, and technical dimensions. Despite its importance, empirical evidence on how such competence is acquired during formal education remains limited. This study applies k-modes clustering, an unsupervised machine learning approach, to examine patterns among students in a Project Management course. Analysis draws on a secondary dataset covering demographics, student engagement, and academic performance. The results reveal clusters of students exhibiting heterogeneous learning profiles and pathways relevant for competence development. These findings indicate that students are not homogeneous and that uniform educational approaches may constrain competence development. Building on these results, the study proposes a Data-Driven Framework for Competence-Oriented Student Segmentation. By providing empirical, data-driven insights into learning heterogeneity, the study contributes to project management education research and offers a methodological basis for further investigation of competence-oriented curriculum design.