Penerapan Data Mining Untuk Rekomendasi Pemilihan Program Studi Perguruan Tinggi Pada Siswa-Siswi SMA Negeri 1 Lakbok Dengan Metode K-Means Clustering

Abstract

Many students at SMA Negeri 1 Lakbok often choose their study programs based on the influence of friends or others, without carefully considering whether the program aligns with their interests and talents. As a result, many students drop out of school, feeling they've chosen the wrong program. Therefore, the author conducted a data mining analysis using grade data of class XII MIPA and IPS students. In the analysis, the author used Microsoft Excel and SPSS tools. The method used is the K-Means Clustering method with 242 MIPA student data and 92 IPS student data, 19 attributes and 10 MIPA clusters and 10 IPS clusters. The number of MIPA Microsoft Excel calculations is 2 large, namely cluster 3 there are 43 data recommended to enter mathematics education, cluster 7 there are 53 data recommended to enter chemical engineering. The number of calculations for Microsoft Excel IPS is 2 large, namely cluster 3 contains 16 data recommended to enter law, cluster 5 contains 12 data recommended to enter geography education. And the number of calculations for SPSS MIPA is 2 large, namely cluster 1 contains 39 data recommended to enter informatics engineering, cluster 5 contains 40 data recommended to enter Indonesian language education. The number of calculations for SPSS IPS is 2 large, namely cluster 2 contains 14 data recommended to enter accounting, cluster 7 contains 17 data recommended to enter Indonesian language education.