The Use of Technology in Improving Understanding of Student Learning Performance Patterns

This study aims to analyze the patterns of students' academic performance based on final semester exam scores, attendance, and task participation using the Principal Component Analysis (PCA) approach and the k-means clustering algorithm. The data used in the study were collected from 50 students and included exam scores, attendance rates, and task participation. The PCA method was employed to reduce the dimensionality of the data, resulting in two principal components (PC1 and PC2) that explained 74.57% of the data variability. Subsequently, the k-means algorithm was applied to cluster students into three groups based on their performance patterns. The clustering results revealed three main clusters: Cluster A (low performance), Cluster B (moderate performance), and Cluster C (high performance). These findings indicate that students' academic performance can be influenced by various factors, including attendance, participation, and scores, highlighting the need for more personalized and adaptive learning approaches tailored to each student's characteristics.