Sari, Fitri Indah (2025) Klasterisasi Industri Kecil Menengah (IKM) di Kota Surabaya Menggunakan Metode Balanced Iterative Reducing and Clustering Using Hierarchies (BIRCH). Undergraduate thesis, Universitas Pembangunan Nasional Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
21083010025_COVER.pdf Download (1MB) |
|
Text (Bab 1)
21083010025_BAB 1.pdf Download (24kB) |
|
Text (Bab 2)
21083010025_BAB 2.pdf Restricted to Registered users only until 18 June 2028. Download (315kB) | Request a copy |
|
Text (Bab 3)
21083010025_BAB 3.pdf Restricted to Registered users only until 18 June 2028. Download (156kB) | Request a copy |
|
Text (Bab 4)
21083010025_BAB 4.pdf Restricted to Registered users only until 18 June 2028. Download (1MB) | Request a copy |
|
Text (Bab 5)
21083010025_BAB 5.pdf Download (16kB) |
|
Text (Daftar Pustaka)
21083010025_DAFTAR PUSTAKA.pdf Download (325kB) |
|
Text (Lampiran)
21083010025_LAMPIRAN.pdf Restricted to Registered users only until 18 June 2028. Download (242kB) | Request a copy |
Abstract
Small and Medium Industries (SMIs) have a strategic role in driving local economic growth, including in Surabaya City. However, the main problem faced by the local government is the suboptimal strategy of coaching and development of SMEs due to the absence of proper segmentation based on business characteristics. This lack of integration has led to the allocation of resources and policies that are general in nature and less responsive to the specific needs of each group of SMEs. Therefore, an objective analytical approach is needed to cluster SMEs based on business attributes to support more effective and targeted decision-making. This study aims to apply the Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) clustering method in grouping SMEs in Surabaya based on a combination of numerical and categorical variables, namely land area, initial capital, number of workers, business scale, business type, and business risk. The selection of BIRCH method is based on its efficient advantage in handling large datasets with hierarchical data structure. Clustering was conducted on 31,465 SME entities using the six main variables. The clustering results formed three main clusters with a distribution of members of 24, 211, and 31,230 entities. Evaluation using a silhouette score of 0.89 indicates an excellent quality of separation between clusters, with a high degree of internal similarity and significant differences between groups. In addition, the proposed web-based system using the Streamlit framework allows users to interact with the analysis results in an intuitive and easy-to-understand manner, thus supporting more effective decision-making.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Data Science | ||||||||||||
| Depositing User: | Fitri Indah Sari | ||||||||||||
| Date Deposited: | 19 Jun 2025 01:23 | ||||||||||||
| Last Modified: | 19 Jun 2025 01:23 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/38268 |
Actions (login required)
 |
View Item |