Implementation of Data Mining Using the K-Means Algorithm to Group Students Based on Academic Performance

Abstract

Data clustering is a critical technique in data mining that identifies patterns or groups within large datasets. This study applies the K-Means algorithm to cluster students from an Islamic boarding school based on their academic performance. The K-Means algorithm was chosen due to its ability to divide data into homogeneous clusters, facilitating a better understanding of academic characteristics for each group. Data from students' test scores—including written tests, oral exams, and classical Islamic book comprehension—were analyzed using Python. The analysis included data collection, preprocessing, determining the optimal number of clusters (K), implementing the K-Means algorithm, and validating clustering outcomes using the Davies-Bouldin Index (DBI). Results demonstrated that students could be grouped into ten clusters, with key insights to improve teaching strategies. Data mining is a process that uses statistical techniques, mathematics, artificial intelligence, and machine learning to interact with, identify useful information, and extract knowledge from various large databases.[1] Data mining is a process that uses statistical techniques, mathematics, artificial intelligence, and machine learning to interact with, identify useful information, and extract knowledge from various large databases. [2] The purpose of this research is to group data of outstanding class students so that in the learning process at school, it is easier to facilitate education according to the students' abilities.[3]