PENGELOMPOKAN UMKM DI KABUPATEN MALANG DENGAN METODE ENSEMBLE ROBUST CLUSTERING USING LINKS (ROCK)

Purwadwika, Reza Sadiya (2025) PENGELOMPOKAN UMKM DI KABUPATEN MALANG DENGAN METODE ENSEMBLE ROBUST CLUSTERING USING LINKS (ROCK). Undergraduate thesis, UPN Veteran Jawa Timur.

	Text 21083010026_Cover.pdf Restricted to Repository staff only Download (2MB)
	Text (Bab 1) 21083010026_Bab 1.pdf Download (254kB)
	Text (Bab 2) 21083010026_Bab 2.pdf Restricted to Repository staff only until 25 July 2028. Download (526kB)
	Text (Bab 3) 21083010026_Bab 3.pdf Restricted to Repository staff only until 25 July 2028. Download (473kB)
	Text (Bab 4) 21083010026_Bab 4.pdf Restricted to Repository staff only until 25 July 2028. Download (6MB)
	Text (Bab 5) 21083010026_Bab 5.pdf Restricted to Repository staff only until 25 July 2028. Download (220kB)
	Text (Daftar Pustaka) 21083010026_Daftar Pustaka.pdf Download (193kB)
	Text (Lampiran) 21083010026_Lampiran.pdf Restricted to Repository staff only until 25 July 2028. Download (442kB)

Abstract

Micro, Small, and Medium Enterprises (MSMEs) are the backbone of Indonesia’s economy, including in Malang Regency, which has strong growth potential in the food, beverage, and souvenir sectors. However, the mapping of MSME business characteristics which involve both numerical and categorical data has not been optimally implemented, making it difficult for local governments to design targeted development strategies. This study addresses the problem of accurately clustering MSMEs while considering the complexity of their business variables. The method used is Ensemble Robust Clustering using Links (ROCK), which combines the advantages of numerical data clustering using Agglomerative Hierarchical Clustering and categorical data clustering using ROCK, enabling the effective integration of both variable types. The analytical process includes preprocessing steps such as outlier handling, numerical variable standardization using Z-score, and categorical variable encoding using Label Encoding. The urgency of this research lies in the need for accurate MSME segmentation to support business digitalization and data-driven policymaking. The innovation of this study, compared to previous research, is the application of the ensemble ROCK method to MSME data with the addition of strategic variables such as the involvement of online motorcycle taxis (ojol) as an indicator of digital readiness an aspect that has not been widely explored. This research aims to produce an informative and valid MSME clustering model for Malang Regency, as well as the development of a web-based graphical user interface (GUI) for interactive visualization of the clustering results. These findings are expected to serve as a foundation for designing more targeted and adaptive MSME development policies in response to digital economic trends.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Hindrayani, Kartika Maulida	NIDN0009099205	kartikamaulida.ds@upnjatim.ac.id
Thesis advisor	Damaliana, Aviolla Terza	NIDN0002089402	aviolla.terza.sada@upnjatim.ac.id

Subjects:

H Social Sciences > HD Industries. Land use. Labor
H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management
Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science

Depositing User:

Reza Sadiya Purwadwika

Date Deposited:

28 Jul 2025 07:29

Last Modified:

28 Jul 2025 07:29

URI:

https://repository.upnjatim.ac.id/id/eprint/40863