PEMODELAN RESTOCK OBAT BERDASARKAN VARIABEL PENGUKURAN INVENTORY UNTUK PENGAMBILAN KEPUTUSAN PENGADAAN DI RUMAH SAKIT XYZ

Adinda Syakira Suciati, . (2025) PEMODELAN RESTOCK OBAT BERDASARKAN VARIABEL PENGUKURAN INVENTORY UNTUK PENGAMBILAN KEPUTUSAN PENGADAAN DI RUMAH SAKIT XYZ. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (11kB)
[img] Text
AWAL.pdf
Download (753kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (43kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (346kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (106kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (680kB)
[img] Text
BAB 5.pdf
Download (12kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (101kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (80kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (15MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (423kB)

Abstract

Effective management of drug inventory is a crucial aspect in supporting the smooth operation and quality of healthcare services in hospitals. One common issue encountered is the inaccuracy in determining restock needs, which can lead to stockouts of essential medicines or excessive inventory that results in waste. This study aims to develop a decision model for drug restocking using two Decision Tree algorithms: C4.5 and CART. The models are constructed based on inventory measurement variables that reflect both actual and historical stock conditions, such as Consumption Average (CA), Lead Time (LT), Safety Stock (SS), minimum stock level (Smin), maximum stock level (Smax), order quantity (Q), real stock, and Day Sales Inventory (DSI). Model performance was evaluated using the 10-Fold Cross Validation method with accuracy, precision, recall, and F1-score as the evaluation metrics. The results show that the C4.5 model outperforms CART, achieving an accuracy of 97.5%, compared to 92.9% for the CART model. Based on these findings, the C4.5 model is recommended as a more reliable approach to support automated decision-making for drug restocking at XYZ Hospital.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110312034] [Pembimbing: Siti Rohana Nasution] [Penguji 1: Alina Cynthia Dewi] [Penguji 2: M. Rachman Waluyo]
Uncontrolled Keywords: Drug Restocking, Decision Tree, C4.5, CART, K-Fold Cross Validation
Subjects: Q Science > QA Mathematics > QA76 Computer software
T Technology > T Technology (General)
Divisions: Fakultas Teknik > Program Studi Teknik Industri (S1)
Depositing User: ADINDA SYAKIRA SUCIATI
Date Deposited: 01 Aug 2025 06:51
Last Modified: 01 Aug 2025 06:54
URI: http://repository.upnvj.ac.id/id/eprint/39178

Actions (login required)

View Item View Item