An integrated clustering method for pedagogical performance

We present an interdisciplinary approach to data clustering, based on algorithm originally developed for the Big Data Modelling of Sustainable Development Goals (BDMSDG). Its application context combines mechanics machine learning techniques with underlying pedagogical domain knowledge–unifying narratives scientists and educationists in searching potentially useful information historical data. From initial structure masking, results from multiple samples identified set two five clusters, reveal a consistent number three clear clusters. discuss technical soft perspectives stimulate interdisciplinarity support ​decision making. explain how findings this paper not only continuity on–going clustering optimisation, but also intriguing starting point discussions aimed at enhancement students performance.