RANCANG BANGUN WEBSITE KEBUTUHAN SPAREPART KULKAS MENGGUNAKAN ALGORITMA RANDOM FOREST (STUDI KASUS PADA PT XYZ)

Talitha Luthfi Endriyanti, . (2026) RANCANG BANGUN WEBSITE KEBUTUHAN SPAREPART KULKAS MENGGUNAKAN ALGORITMA RANDOM FOREST (STUDI KASUS PADA PT XYZ). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

	Text ABSTRAK.pdf Download (157kB)
	Text AWAL.pdf Download (1MB)
	Text BAB I.pdf Restricted to Repository UPNVJ Only Download (378kB)
	Text BAB II.pdf Restricted to Repository UPNVJ Only Download (764kB)
	Text BAB III.pdf Restricted to Repository UPNVJ Only Download (486kB)
	Text BAB IV.pdf Restricted to Repository UPNVJ Only Download (4MB)
	Text BAB V.pdf Download (201kB)
	Text DAFTAR PUSTAKA.pdf Download (212kB)
	Text RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (114kB)
	Text LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (556kB)
	Text HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (31MB)
	Text ARTIKEL KI.pdf Restricted to Repository staff only Download (483kB)

Abstract

PT XYZ is a company that operates a workshop specializing in refrigerator maintenance and repair to support its product distribution activities. Currently, spare part management is still carried out manually, which may result in insufficient inventory when demand increases. In addition, spare part demand forecasting is still performed subjectively using a minimum stock approach, leading to less accurate decision-making. This study aims to develop a web-based application for managing spare part data, recording incoming and usage transactions, and predicting spare part demand equipped with a purchase recommendation feature. The developed application implements the Random Forest Regression algorithm to perform predictions based on historical spare part usage data processed on a daily basis and aggregated into monthly data. The experimental results on daily data show a Mean Absolute Error (MAE) of 0.46, a Root Mean Square Error (RMSE) of 0.65, a Mean Absolute Percentage Error (MAPE) of 29.67%, and an R-Squared value of 0.49. Meanwhile, the model evaluated using aggregated monthly data achieved better performance, with an MAE of 0.82, an RMSE of 1.16, a MAPE of 18.65%, and an R-Squared value of 0.96. These results indicate that the model performs more accurately and consistently when applied to aggregated monthly data. The application was designed and developed through several stages, including requirements analysis, user interface design, model development, application development covering both backend and frontend implementation, and database design. Application testing was conducted using three approaches, namely User Acceptance Testing (UAT), Black Box Testing, and Non-Functional Testing. User Acceptance Testing and Black Box Testing were performed to ensure that all application features functioned according to user requirements, while Non Functional Testing was conducted to verify that the application provides good performance and reliable operation. The results of the User Acceptance Testing indicate that the application achieved a user acceptance level of 90.53%, which is categorized as very good. These findings demonstrate that the developed application can effectively support spare part management and spare part demand planning.

Item Type:	Thesis (Skripsi)
Additional Information:	[No.Panggil: 2210511026] [Pembimbing 1: Muhammad Adrezo] [Pembimbing 2: Radinal Setyadinsa] [Penguji 1: Musthofa Galih Pradana] [Penguji 2: Kharisma Wiati Gusti]
Uncontrolled Keywords:	sparepart, inventory management, stock planning, demand prediction, Random Forest Regression
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Divisions:	Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User:	TALITHA LUTHFI ENDRIYANTI
Date Deposited:	28 Jul 2026 16:02
Last Modified:	28 Aug 2026 06:30
URI:	http://repository.upnvj.ac.id/id/eprint/51923

Actions (login required)

View Item