Sustained inflation will have a negative impact on the economy. Low and stable inflation can be a good stimulator for economic growth. That is why the government needs to control the inflation rate so that it is neither too high nor too low. As a strategic indicator, it is important to study inflation in terms of both calculation and grouping. This study aims to classify inflation cities and see whether there are spatial relationships between inflation cities in Sumatra. The research method used is the K-Means Clustering Algorithm with the number of clusters 3. Using the K-Means Algorithm method, cities with a high inflation rate, medium (average) or low inflation rate can be grouped. The results showed that cluster 1 consisted of 7 districts/cities (ie Meulaboh; Banda Aceh; Sibolga; Padang Sidempuan; Bukittinggi; Pekanbaru; and Tanjung Pandan), cluster 2 contained 5 districts/cities (ie Gunung Sitoli; Padang; Bungo; Jambi; and Pangkal Pinang), and in cluster 3 there are 12 districts/cities. Meanwhile, in terms of the spatial relationship between one regency/city, the regencies/cities that calculate inflation throughout Sumatra have a close relationship with the condition of neighboring regencies/cities. Keyword : Clustering; Inflation; K-Means Algorithm;
Copyrights © 2022