Evaluation of Civil Engineering Students' Academic Performance Using Fuzzy C-Means Clustering

Abstrak

Students' academic performance can be measured through their mastery of the core competencies they acquire or learn in teaching and learning activities at their respective universities. This study uses the fuzzy c-means clustering method as a form of educational data mining. The fuzzy c-means clustering method is used because this method is able to group student data with criteria that can be used as a reference in implementing academic performance evaluations. The clustering results are evaluated using the silhouette coefficient value. The data processing process with the fuzzy c-means clustering algorithm shows three clusters with different centroid values. The first cluster with centroids (83.77, 79.48, 82.73) and consisting of 90 students is the cluster with the best academic performance evaluation results. Meanwhile, the third cluster with centroids (63.66, 64.82, 59.96) and consisting of 12 students is the most worrying academic performance evaluation result. These results serve as a reference for study program managers so that treatment of students with worrying academic performance can be made more strategic.