Profiles associated with systemic and sustainability competence in higher education identified through learning analytics

The development of systems thinking and sustainability competence has become a strategic priority in higher education, requiring educational approaches capable of identifying diverse learning patterns among students. In this context, learning analytics combined with unsupervised clustering offers opportunities to explore large-scale educational data and identify heterogeneous student learning patterns. This study aimed to identify learning profiles associated with systems thinking and sustainability competence using institutional learning analytics data from higher education. The study analyzed 51,492 student-term observations obtained from the Data Hub of the Institute for the Future of Education. Academic performance, learning engagement, and competency-related indicators were examined using K-means clustering to identify learning profiles. Principal Component Analysis was used to visualize cluster separation, while Chi-square tests and Cramér’s V were applied to evaluate associations between learning profiles and demographic and academic variables. Three distinct learning profiles were identified. One profile was characterized by lower academic performance despite maintaining levels of participation comparable to the other groups, whereas two profiles showed similarly high academic performance but differed in their levels of engagement and the number of competency-related indicators. Program major exhibited the strongest association with learning profile membership, while nationality and gender showed statistically significant but weak associations, indicating limited practical influence on profile differentiation. These findings demonstrate that learning analytics can effectively identify heterogeneous learning profiles associated with academic performance, engagement, and competency-related indicators in higher education. Rather than directly measuring systems thinking and sustainability competence, the proposed approach provides a data-driven framework for understanding learning patterns that can support curriculum design, personalized educational interventions, and continuous improvement initiatives in competency-based higher education.