PENERAPAN DATA MINING DALAM MENGELOMPOKKAN KUNJUNGAN WISATAWAN DI KOTA YOGYAKARTA MENGGUNAKAN METODE K-MEANS

Abstract

Yogyakarta is one of the cities in Indonesia that has a tourist attraction and is a tourist destination that is most in demand by tourists, seen from the number of tourist visits that are increasing from year to year. Apart from being a tourist city, Yogyakarta is a city of students, a city of culture and a city of struggle. Because Yogyakarta is called a tourist city, there are many kinds of tourist objects offered by the City of Yogyakarta. In this case, the application of data mining can be a solution in analyzing data. Clustering is included in descriptive methods, and also includes unsupervised learning where there is no previous object class definition. So that clustering can be used to determine class labels for data whose class is not known. The K-Means method is included in partitioning clustering which separates data into separate parts. The K-Means method is well known for its ease and ability to group large data and outliers very quickly. from the data entered and has been processed through the K-Means algorithm method that has performed iterations 5 times by choosing cluster 1, cluster 2, cluster 3 randomly (random) with cluster 1 having 24 data with a percentage of (50%), cluster 2 has 11 data with a percentage of (23%), and cluster 3 has 13 data with a percentage of (27%).