Penerapan Metode K-Means Dan Harmony Search Untuk Seleksi Fitur Pada Penentuan Credit Score

Puspitasari, Anita (2025) Penerapan Metode K-Means Dan Harmony Search Untuk Seleksi Fitur Pada Penentuan Credit Score. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010015.-cover.pdf Download (2MB)
	Text (Bab 1) 20081010015.-bab1.pdf Download (208kB)
	Text (Bab 2) 20081010015.-bab2.pdf Restricted to Repository staff only until 5 January 2028. Download (357kB)
	Text (Bab 3) 20081010015.-bab3.pdf Restricted to Repository staff only until 5 January 2028. Download (666kB)
	Text (Bab 4) 20081010015.-bab4.pdf Restricted to Repository staff only until 5 January 2028. Download (2MB)
	Text (Bab 5) 20081010015.-bab5.pdf Download (285kB)
	Text (Daftar Pustaka) 20081010015.-daftarpustaka.pdf Download (171kB)
	Text (Lampiran) 20081010015.-lampiran.pdf Restricted to Repository staff only Download (454kB)

Abstract

Credit is a payment mechanism provided by financial institutions in the form of loan funds. Creditworthiness assessment, commonly referred to as a credit score, plays a crucial role in estimating lending risks to customers. The main challenge in developing a credit scoring model lies in the large number of transaction features that are irrelevant and redundant, which leads to high computational costs. This study proposes a feature selection method using the K-Means and Harmony Search algorithms as a solution to this problem. K-Means is employed to analyze distance based to identify representative features, while Harmony Search is utilized to determine the most relevant feature combinations. The results of this research indicate that the proposed method not only improves prediction accuracy but also enhances computational efficiency. The model achieved a performance of MAPE = 3.2%, RMSE = 25, and R² = 0.86, with a training computation time of 0.0165 seconds and prediction time of 0.0041 seconds. These results demonstrate the effectiveness of combining K-Means and Harmony Search methods in simplifying data for credit scoring models without compromising data quality. Keywords: Credit Score, Feature Selection, K-Means, Harmony Search.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Mandyartha, Eka Prakarsa	NIP19880525 201803 1 001	eka_prakarsa.fik@upnjatim.ac.id
Thesis advisor	Haromainy, Muhammad Muharrom Al	NIP19950601 202203 1 006	muhammad.muharrom.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General) > T58.6-58.62 Management Information Systems

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Anita Anita Anita Puspitasari

Date Deposited:

05 Jan 2026 07:28

Last Modified:

05 Jan 2026 07:28

URI:

https://repository.upnjatim.ac.id/id/eprint/48554