Using Self-Organizing Map (SOM) for Clustering and Visualization of New Students based on Grades

Abstract

Student grouping, particularly in high school, is a necessary process to divide and classify students into classes based on their abilities and interests. Each school may have different approaches to decide the grouping, but most schools use academic grades. The activity occurs every new academic year and schools with plenty of new students registered may feel a bit overwhelmed with this grouping assignment. A decision support system which can automatically perform grouping on a list of students may be able to help the school’s staffs with this repetitive task. A self-organizing map (SOM) is an example of unsupervised learning algorithm using an artificial neural network structure to produce a low dimensional representation from a given input. However, SOM is also known as one of clustering techniques, since dimensionality reduction may also be seen as reducing (or clustering) input data to lower dimensions (or clusters). This research aims to group new enrolled students to a high school based on their academic grades using a SOM learning algorithm. The grades came from their rapport books and national examination results from their previous study. The resulting groups are three distinct clusters which represents Life Sciences, Social Sciences, and Linguistics study areas.