<![CDATA[Student internet networks in online-based lectures during the pandemic yesterday were a must-have for students. This research has the aim of providing awareness of Satya Wacana Christian University Faculty of Information Technology data collection about the effect of internet quality on student learning intentions which can be analyzed with technology using K-Means Clustering. K-Means Clustering is used to group data sets into several clusters. Data features in the form of an internet network quality scale based on perceived service quality and student learning intentions obtained from Satya Wacana Christian University students, Faculty of Information Technology, Informatics Engineering study program through distributing questionnaires. The results of the questionnaire in the form of numbers on a Lickert scale are used in RapidMiner for clustering using K-Means Clustering. The results of the analysis on the student data studied have 37 data having many clusters k = 4 obtained using Elbow Method. Of the student correspondents who have good internet quality, namely C2 by 27.02% and C4 by 8.1%, only 3 correspondents or 8.1% of the total data have good learning intentions. While the results of students internet quality are poor, students study intentions are not significant because the difference in data between C1 and C3 is only a little. The results of C1, namely students who have poor internet quality and poor learning intentions, are only 11 correspondents or 29,72% of the total data while C3, which includes students who have poor internet quality but have good learning intentions, is 13 correspondents or 35.13% of total data. Based on this research, K-Means Clustering can be used to group students in viewing and making decisions online learning.]]>
