Klasterisasi Tingkat Kesejahteraan Masyarakat Menggunakan Metode Self Organizing Maps

Afidria, Zulfa Febi (2025) Klasterisasi Tingkat Kesejahteraan Masyarakat Menggunakan Metode Self Organizing Maps. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21083010096_Cover.pdf Download (741kB)
	Text (Bab 1) 21083010096_Bab I.pdf Download (95kB)
	Text (Bab 2) 21083010096_Bab II.pdf Restricted to Registered users only until 20 June 2028. Download (296kB)
	Text (Bab 3) 21083010096_Bab III.pdf Restricted to Registered users only until 20 June 2028. Download (328kB)
	Text (Bab 4) 21083010096_Bab IV.pdf Restricted to Registered users only until 20 June 2028. Download (1MB)
	Text (Bab 5) 21083010096_Bab V.pdf Download (10kB)
	Text (Daftar Pustaka) 21083010096_Daftar Pustaka.pdf Download (160kB)
	Text (Lampiran) 21083010096_Lampiran.pdf Restricted to Registered users only until 20 June 2028. Download (209kB)

Abstract

Community welfare is one of the key indicators in determining the success of regional development. Although Java Island is the center of national economic growth, welfare disparities between regions remain high, as reflected in disparities in poverty rates, unemployment, and access to basic services. This study examines these issues with the aim of grouping regions based on objective and comprehensive welfare indicators. The methods used are a combination of Uniform Manifold Approximation and Projection (UMAP) for dimension reduction and SelfOrganizing Maps (SOM) as a clustering algorithm. UMAP helps filter out irrelevant information from high-dimensional data, while SOM maps regions into groups with similar welfare characteristics. Low levels of community welfare without proper handling can widen social gaps, exacerbate poverty, and hinder regional economic growth. Therefore, an analytical model like SOM is needed to support fairer and more effective policies. The innovation of this research lies in the application of the combination of UMAP and SOM in the context of comprehensive welfare mapping on Java Island, which has been rarely done before. Based on the evaluation results using the silhouette coefficient, the highest score obtained was 0.7062 with an optimal number of three clusters. Cluster 1 consists of 27 districts/cities with high welfare, Cluster 2 includes 17 regions with moderate welfare, and Cluster 3 covers 75 regions with low welfare. These results are expected to serve as the basis for more adaptive policies and support the achievement of the SDGs 2030.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Trimono, Trimono	NIDN0008099501	trimono.stat@upnjatim.ac.id
Thesis advisor	Prasetya, Dwi Arman	NIDN0005128001	arman.prasetya.sada@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics
Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Zulfa Afidria

Date Deposited:

20 Jun 2025 01:19

Last Modified:

20 Jun 2025 01:19

URI:

https://repository.upnjatim.ac.id/id/eprint/38760