Penerapan Metode K-Means Clustering terhadap Ekspor Buah-Buahan Tahunan Menurut Negara Tujuan Utama

Abstract

Cluster analysis is the process of dividing data in a set into several groups whose data similarity in one group is greater than the similarity of the data with data in other groups.The aim of this research using the K-Means Clustering method is to group and determine the level of export of fruit by destination country with high and low level categories. There are two variables that can be measured for this grouping, namely net weight (tons) and FOB (US$). The data collection method used is the documentation method in the form of secondary data obtained from the website of the Badan Pusat Statistik (BPS). Data processing is done with manual calculations and also with the help of SPSS and R software . From the research results of the K-Means Clustering method with the help of R in determining the number of clusters, 2 clusters are obtained. Cluster 1 is a country with a high level of exports consisting of 4 countries, namely Malaysia, Vietnam, China and Thailand. Cluster 2 is a country with a low export level consisting of 7 countries, namely India, Japan, Hong Kong, the United Arab Emirates, Singapore, Nigeria and other countries. Based on the significance value of each variable is less than 0,05 in the ANOVA table in this study, it can be concluded that the two clusters have significant differences.