SIATECH Student Analytics System: An integrated approach to descriptive, correlational, multivariate and predictive analytics

Abstract

The SIATECH study addresses the need to assess and improve academic satisfaction and performance in education by implementing advanced statistical and machine learning techniques. Using the importance-performance analysis (IPA) model as a basis, the study aims to develop a student analytics system to perform descriptive, correlational, multivariate and predictive analyses, thus providing a comprehensive tool to improve educational processes. This predictive approach offers the possibility of customizing educational interventions, thus improving individual academic outcomes, providing instructors with a clear understanding of student expectations and allowing them to adjust their teaching methods to improve learning. However, from a statistical know-how point of view, the lack of training in data analysis among some teachers may limit the ability to interpret and effectively use the information obtained, highlighting the need to integrate statistical training into teacher training programs, however, SIATECH devises a dynamic platform that is very easy to use and interpret. In summary, SIATECH proves to be a valuable tool for improving educational practices, emphasizing the importance of a data-driven approach to educational decision-making.