Application of Data Mining in Clustering Potential Students Drop Out Using Fuzzy C-Means Algorithm (Case Study: Faculty of Science and Technology UIN Bandung) Ali Rahman (1*) Mohamad Irfan(1) (1) Faiz M Kaffah (1) Irma Rahmawati(1)
1) Universitas Islam Negeri Sunan Gunung Djati Bandung
Abstract
Higher education is an institution that has certain data. Data that is owned by the campus is different, such as financial data, academic data, administrative data, etc. Because of the large amount of data that the faculty has, the data must be processed into useful information such as information on students who have the potential to drop out. This study uses a fuzzy c-means algorithm with sample data from 2014, 2015 and 2016 students for all majors in the Faculty of Science and Technology, each batch consists of 35 students, so there are 105 data in total. There are 3 criteria that are calculated in this study, which are based on leave data, achievement index data every semester and spp payment data. Fuzzy C-Means Algorithm Analysis is a process carried out to find out detailed calculations that are mathematical and get iteration values of more than 10% and data accuracy that can reach 95%
