Klasterisasi Data Kemiskinan di Kabupaten/Kota Provinsi Nusa Tenggara Timur Menggunakan Algoritma K-Means
Total View This Week0
Total View This Week0
Institusion
Universitas Katolik Widya Mandira Kupang
Author
DJEMANI, Fridolin Ciciclaudia
Subject
HC Economic History and Conditions
Datestamp
2024-05-22 02:17:49
Abstract :
The province of East Nusa Tenggara (NTT) in Indonesia faces significant challenges in addressing poverty. According to data from the Central Statistics Agency (BPS), NTT ranked third among the poorest provinces in Indonesia in 2023. Poverty is defined as the inability to meet basic needs despite having the ability to work. Factors such as uneven socio-economic development contribute to poverty and socio-economic disparities across various regencies/cities in NTT. This study applies the k-means clustering algorithm to group regencies/cities based on poverty information data. The results indicate three clusters that distinguish levels of socio-economic development and poverty. Cluster 1 shows low socio-economic development, cluster 0 shows moderate socio-economic development, and cluster 2 shows high socio-economic development. There are 5 regencies in cluster 1, 16 regencies in cluster 0, and 1 city in cluster 2. The evaluation of the number of clusters shows that using three clusters has a lower Davies-Bouldin Index (DBI) value of 0.629, indicating that k=3 is more optimal for data clustering. This study's findings are expected to provide better insights into uneven socio-economic development and enable more accurate resource allocation to reduce socio-economic disparities and poverty in NTT.
The province of East Nusa Tenggara (NTT) in Indonesia faces significant challenges in addressing poverty. According to data from the Central Statistics Agency (BPS), NTT ranked third among the poorest provinces in Indonesia in 2023. Poverty is defined as the inability to meet basic needs despite having the ability to work. Factors such as uneven socio-economic development contribute to poverty and socio-economic disparities across various regencies/cities in NTT. This study applies the k-means clustering algorithm to group regencies/cities based on poverty information data. The results indicate three clusters that distinguish levels of socio-economic development and poverty. Cluster 1 shows low socio-economic development, cluster 0 shows moderate socio-economic development, and cluster 2 shows high socio-economic development. There are 5 regencies in cluster 1, 16 regencies in cluster 0, and 1 city in cluster 2. The evaluation of the number of clusters shows that using three clusters has a lower Davies-Bouldin Index (DBI) value of 0.629, indicating that k=3 is more optimal for data clustering. This study's findings are expected to provide better insights into uneven socio-economic development and enable more accurate resource allocation to reduce socio-economic disparities and poverty in NTT.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
