Putri, Amadea Syahbani Rachela (2026) Pengembangan Model Klasifikasi Risiko Keterlambatan Impor Bahan Baku Baja Hot Rolled Coil (HRC) Berdasarkan Indikator Supply Chain Visibility Pada PT Berjaya Mandiri Indonesia. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text
22012010385 - COVER.pdf Download (783kB) |
|
Text (bab 1)
22012010385 - BAB 1.pdf Download (393kB) |
|
Text (bab 2)
22012010385 - BAB 2.pdf Restricted to Repository staff only until 20 July 2029. Download (359kB) |
|
Text (bab 3)
22012010385 - BAB 3.pdf Restricted to Repository staff only until 20 July 2029. Download (375kB) |
|
Text (bab 4)
22012010385 - BAB 4.pdf Restricted to Repository staff only until 20 July 2029. Download (798kB) |
|
Text (bab 5)
22012010385 - BAB 5.pdf Download (202kB) |
|
Text (daftar pustaka)
22012010385 - DAFTAR PUSTAKA.pdf Download (204kB) |
|
Text (lampiran)
22012010385 - LAMPIRAN.pdf Restricted to Repository staff only until 20 July 2029. Download (911kB) |
Abstract
Delays in the importation of Hot Rolled Coil (HRC) raw materials can disrupt supply chain continuity and production processes at PT Berjaya Mandiri Indonesia. This study aims to develop a machine learning-based import delay risk classification model to support more objective risk identification. A quantitative approach was employed using 200 historical HRC import records collected between 2020 and 2025. The variables analyzed include delay days, customs clearance duration, Estimated Time of Arrival (ETA) deviation, shipment monitoring status, import document completeness, and document clarification duration. These variables were weighted using a risk scoring method to generate three risk categories: Low Risk, Medium Risk, and High Risk. The classification model was developed using three machine learning algorithms and evaluated through stratified 5-fold cross-validation based on accuracy, precision, recall, and F1-score to determine the most suitable model for supporting the risk identification process. The results indicate that the Decision Tree algorithm achieved the best performance, with a macro-F1 score of 0.965, while also providing greater interpretability, thereby facilitating risk identification and supporting operational decision-making. Validation through confirmation interviews further demonstrated that the model aligns with the company's operational requirements and has the potential to enhance supply chain visibility by enabling more systematic risk identification as a basis for decision-making in raw material import management. Keywords: Supply Chain Visibility; Risk Scoring; Machine Learning; Import Delay Risk; Supply Chain Risk Management.
| Item Type: | Thesis (Undergraduate) | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||
| Subjects: | H Social Sciences > HD Industries. Land use. Labor H Social Sciences > HD Industries. Land use. Labor > HD38.5 Supply Chain Management |
||||||||
| Divisions: | Faculty of Economic and Business > Departement of Management | ||||||||
| Depositing User: | Amadea Syahbani Rachela Putri | ||||||||
| Date Deposited: | 21 Jul 2026 04:11 | ||||||||
| Last Modified: | 21 Jul 2026 06:44 | ||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/56475 |
Actions (login required)
 |
View Item |