Monitoring Students Performance using Self Organizing Map Trend Clustering

Abstract

The analysis of relation between student performance and other variables in education setting is often useful in identifying influential factors on performance. Consequently, the need for adopting an effective tool to process these big data has risen. The analysis of big data will transform passive data into useful information. Data mining is referred to an analytic process designed that discovers data patterns and relationships between datasets. In this study, clustering is used to cluster student grade datasets to generate trend line clusters. The aim of the study is to assist lecturers and academic advisors to recognize the progress of their students.