Implementation of K-Means clustering on student learning achievements based on social economic and social related

Abstract

The premise of this study is that education is an intentional attempt to discover pupils' potential. Students receive learning outcomes for every course they have taken at the conclusion of each semester, along with learning successes or the Cumulative Achievement Index. Using the K-Means Clustering approach is one way to categorize pupils based on their cumulative achievement index. This study uses a combination of quantitative and qualitative methodologies, which is known as a mix-method study. A sequential explanatory design is used in this investigation. This study's findings include the application of the Data Mining Algorithm to classify students' learning outcomes in the Informatics Vocational Education Study Program according to socioeconomic and social factors, particularly if they major in computer education. Because of this, students require computers and other learning aids in order to facilitate learning in the classroom and to avoid any problems when the lecturer assigns homework.

Keywords

• k-means clustering algorithm
• social and socioeconomic
• student learning achievement