SISTEM PENDUKUNG KEPUTUSAN KINERJA DOSEN MENGGUNAKAN SISTEM KECERDASAN BUATAN BERBASIS ALGORITMA K-MEANS CLUSTERING

Abstract

This study aims to analyze the teaching performance quality of lecturers in the Faculty of Engineering and Computer Science at Universitas Sains Al-Qur'an using an artificial intelligence system based on the K-Means Clustering algorithm. Evaluating lecturer performance is a crucial step in ensuring the effectiveness and efficiency of the teaching process which includes pedagogical, professional, personality, and social indicators. Conventional approaches are often complex and ineffective in identifying in-depth performance patterns. The K-Means Clustering algorithm enables the grouping of evaluation data into clusters based on feature similarities, thus revealing patterns that are difficult to discern manually. The data used in this study comes from lecturer evaluation questionnaires completed by students during the even semester of the 2022/2023 academic year. The results showed that the clustering process yielded good separation with a Silhouette Score of 0.593 and a Davies-Bouldin Index of 0.606. These findings indicate that the data within the clusters are more similar to each other than to data in different clusters, suggesting effective clustering. The insights gained from this study are expected to be valuable for the management and development of teaching quality and to promote the use of artificial intelligence technology in higher education evaluations. The findings of this study are also expected to be adaptable by other educational institutions to improve academic excellence standards and produce high-quality graduates.