Penerapan Normalisasi Data Dalam Mengelompokkan Data Mahasiswa Dengan Menggunakan Metode K-Means Untuk Menentukan Prioritas Bantuan Uang Kuliah Tunggal

Abstract

At Budi Darma University there are obstacles in providing UKT rocks where it is profitable and less targeted for students who get it. This happened because those who deserved this assistance were students who had difficulty in costs, therefore we needed a way by grouping student data based on their social level. In determining the students who deserve to get the rock, they can use the data of students who are undergoing their studies at Budi Darma University. By digging up information based on student data. So that the data can be used first, the data normalization is carried out in order to obtain more accurate data. Where student data can be grouped correctly, data normalization must be carried out. One of the normalization methods that are often used in normalizing data is the decimal scaling method which is a data transformation method with normalization to equalize the range of values ​​on each attribute with a certain scale by moving the decimal value from data in the desired direction After the data is normalized, the next process is to explore student data information by applying data mining. The application of data mining is carried out to obtain information in the form of student data groups that are used as a priority in obtaining UKT assistance. The method used in classifying student data is using the K-Means algorithm. The manual testing method is that there are 3 clusters where the number of clusters 0 cluster 1 and cluster 3 is the same as testing data mining applications, namely rapidminer so that those who deserve to be prioritized get tuition assistance based on the sample, namely cluster / grouping 0 which consists of 22 people. This study aims to see the effect of applying data normalization in the K-Means method to classify student data which is used as a recommendation in the selection of UKT assistance.