Klasterisasi Pendidikan Masyarakat Untuk Mengetahui Daerah Dengan Pendidikan Terendah Menggunakan Algoritma K-Means

Abstract

Education is a basic need for every human being who plays an important role in the future of the nation, because a nation that is said to be advanced can be seen from its good learning system. Successful education is measured by the average number of graduates at various levels of education in various regions. But not all regions are good in the quality of education. One of them is the area in Indonesia, such as the Kapuas district, Central Kalimantan. It is known that in previous years this area lacked improvement in education, causing several areas where people did not go to school or dropped out of school. Many of the problems are caused by economic factors, laziness, lack of motivation about the importance of education, and so on. The previous Covid-19 pandemic was also the reason for the increase in the number of children dropping out of school due to a declining family economy. The number of areas in Kapuas district requires grouping the number of existing villages. The grouping aims to make it easier for the government to pay special attention to areas where education is considered lacking and other purposes are to find out which villages have low levels of education. In grouping, the system applied is data mining using the K-Means Algorithm Clustering method which is processed using rapidminer software. The groupings formed on the education level data of 229 records are 8 clusters where the lowest education villages are stated in (C1) with a total of 33 villages.