Across different Southeast Asian countries, there has been a growing acknowledgment of the importance of global citizenship education as part of the broader goal of developing transversal competencies among students in the formal and informal education sectors (UNESCO, 2016; UNICEF & SEAMEO, 2017). As such, different Southeast Asian countries, individually and collectively, have embarked on efforts to begin clarifying the definitions and frameworks of global citizenship, studying the expressions in existing curricula, planning the processes for curriculum development, teacher development, and material development for their respective educational systems. The goal of these efforts is to define how children in each of the Southeast Asian countries will be educated on what it means to be a global citizen in the 21st century. Part of such processes has involved participating in international largescale assessments that seek to assess students’ global citizenship learning competencies. Based on the global citizenship frameworks used in the large-scale assessment (OECD, 2019; UNICEF & SEAMEO, 2017; 2019), there are now existing data that provide a snapshot of current knowledge, beliefs, attitudes, and behavioral intentions of students related to broad articulations of global citizenship competencies, even before the development of formal global citizenship education curricula. This current research seeks to go beyond descriptive analysis of such data. Instead, data science methodologies are used to provide insights into how the different competencies are structured in the understanding of the students in a country. The objective of this study was to utilize machine learning approaches in data sciences to discover further patterns of relationships in the data from Southeast Asian countries that participated in such large-scale assessments.