Abstract: This research paper explores the application of clustering analysis to analyze student performance data and provide insights for tailored interventions in an educational context. The study utilized the K-means algorithm coupled with scaling techniques and the Elbow method to cluster students based on their academic performance. The dataset comprised course grades, cumulative GPA, and other performance-related metrics of computer science students from Oakland University. The Elbow method determined the optimal number of clusters to be three, and scaling the data significantly improved clustering accuracy. Three distinct clusters were identified: high-performing students, moderate-performing students, and low-performing students. The findings demonstrate the importance of preprocessing steps such as scaling in clustering analysis to ensure accurate representation of student performance patterns. These insights can inform educators in designing targeted interventions to support students at different performance levels, ultimately contributing to improved student outcomes and retention in academic institutions. Keywords: Clustering analysis, K-means algorithm, Student performance, Educational data analysis, Scaling techniques