Grouping of Student Learning Interest Indicators using the Clustering Method (Case Study: MA. Al – Asy'ariah Sunggal)

Abstract

Student learning interest is an important factor in achieving educational outcomes, as it is directly related to their involvement in the learning process. However, in reality, each student has a different character and learning style, often making it difficult for teachers to determine effective and appropriate learning strategies. Therefore, an approach that can objectively identify patterns of student learning interest is needed. This study aims to group students based on three main indicators of learning interest: class activity, academic grades, and involvement in extracurricular activities. The method used is K-Means Clustering, which is a data mining technique for grouping data based on similar characteristics between objects. This research process began with data collection of 508 students of MA Al- Asy'ariah Sunggal in the 2024 academic year, then the data was transformed into numeric form. Next, the K-Means algorithm was implemented using MATLAB R2014b software. The analysis results show that students can be divided into three main clusters, each with different learning interest characteristics. The first cluster consists of students who are less active and do not participate in extracurricular activities, the second cluster contains students with high academic grades but minimal classroom engagement, and the third cluster reflects students who are active both academically and non-academically. These results provide a concrete picture for schools in developing more targeted learning strategies, based on the needs and potential of students in each group.