Implementasi Algoritma Fuzzy C-Means untuk Pengelompokkan Provinsi di Indonesia Berdasarkan Kualitas Perguruan Tinggi

Abstract

The education system in Indonesia is very large and complex with low quality. The quality of Indonesian education can improve, one way is by having equal distribution of education in every province in Indonesia. This equality can be one solution to improve the quality of graduates in Indonesia. This equality can be done by grouping Indonesian provinces with low quality education. One grouping method that can be used is the Fuzzy C-Means algorithm, which is a clustering technique that is determined by the degree of membership in each data point in one cluster. The grouping process was carried out using 136 data on Higher Education Gross Enrollment Rates in 34 provinces from 2019-2022. The data was processed using the Fuzzy C-Means algorithm and then a search for optimal clusters was carried out using the help of the Partition Coefficient Index. Based on testing from 2 to 10 clusters, the optimum cluster is 2 clusters, with a Partition Coefficinet Index value of 0.83491. In the optimum cluster, we get cluster 1 with 20 provinces and cluster 2 with 14 provincial groups. Characteristics resulting from data from 2019 to 2022, cluster 1 has provincial members with the lowest higher education APK compared to cluster 2, especially in cluster 1 members, namely Kep province. Bangka Belitung which has the lowest higher education APK is 2019 with 14.27 APK, 2020 with 14.73 APK, 2021 with 15.23 APK, 2022 14.85 APK.