Application of the K-MEANS Clustering Algorithm for Mapping Open Unemployment Data in Cities/Regencies in Indonesia
This project applies the K-MEANS clustering algorithm to map open unemployment data across cities and regencies in Indonesia. The primary data used comes from the Badan Pusat Statistik (BPS), focusing on the years 2021, 2022, and 2023.
The Elbow Method was employed to determine the optimal number of clusters, resulting in three distinct clusters: low, medium, and high unemployment levels. The quality of clustering was evaluated using the Davies-Bouldin Index, which indicated that the clustering results are of good quality. Geospatial visualizations of the clustering results revealed that high unemployment rates are more dominant on the island of Java, while low unemployment rates are more prevalent on the island of Sulawesi.
This research is intended to provide valuable insights for policymakers in designing more effective unemployment alleviation strategies.
For GIS shapefile maps of district/city boundaries in Indonesia, you can visit Lapak GIS.