Abstract: Academic performance prediction is a challenging task in today's education system, and its analysis plays a crucial role in enhancing the quality of education and supporting decision-making. Evaluating students' performance is of utmost importance for educational institutions as it enables academic leaders to make informed decisions using the vast amount of available data and various algorithms. Clustering, a process of grouping objects based on their similarities is employed in this research to analyze students' performance. Specifically, the K-Means clustering algorithm is utilized to cluster students based on their academic characteristics. This research paper explores the application of data clustering, focusing on the K-Means algorithm, to evaluate students' performance. The findings of this study contribute to the understanding of student performance analysis and provide valuable insights for academic leaders to make data-driven decisions.

Clustering, K-Means Clustering, Students’ Academic Performance