Bagus Rahmadani, . (2026) MONITORING DAN PREDIKSI RISIKO KELULUSAN MAHASISWA DENGAN RANDOM FOREST MELALUI IMPLEMENTASI DASHBOARD. Tugas Akhir thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (237kB) |
|
Text
AWAL.pdf Download (1MB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (309kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (589kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (387kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (7MB) |
|
Text
BAB 5.pdf Download (290kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (316kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (183kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (37MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (741kB) |
Abstract
The high rate of delayed graduation among students in Indonesia underscores the urgent need for a more proactive and data-driven academic monitoring system. This study aims to design and develop the MyPrediction application as a web-based early warning system to predict the risk of delayed graduation among students at UPN "Veteran" Jakarta. The method applied is Random Forest using the CRISP-DM approach, with system development following the RAD methodology. The system is built using a Next.js and FastAPI architecture, equipped with JWT authentication, role-based monitoring dashboards, batch prediction via CSV upload, PDF and Excel export reports, high-risk alerts, and an audit log. Model evaluation results demonstrate excellent performance, with an Accuracy of 99.9%, Balanced Accuracy of 97.8%, F1-Score of 98.7%, and a High Risk Recall of 96.3%. Black Box Testing across 93 scenarios on 14 features confirmed all scenarios performed according to specifications. User Acceptance Testing (UAT) involving three real stakeholders from UPNVJ yielded a Task Success Rate of 100% and a Usability Score of 4.33 out of 5.00 (classified as Very Good), confirming the system's readiness for real-world deployment. MyPrediction is expected to support data-driven strategic decision-making by the BAKK to improve the on-time graduation rate.
| Item Type: | Thesis (Tugas Akhir) |
|---|---|
| Additional Information: | [No.Panggil: 2310501004] [Pembimbing: Tri Rahayu] [Penguji 1: Nur Hafifah Matondang] [Penguji 2: Rio Wirawan] |
| Uncontrolled Keywords: | Early Warning System, Random Forest, Graduation Prediction, Machine Learning, Academic Monitoring |
| Subjects: | Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (DIII) |
| Depositing User: | BAGUS RAHMADANI |
| Date Deposited: | 28 Aug 2026 04:00 |
| Last Modified: | 28 Aug 2026 04:00 |
| URI: | http://repository.upnvj.ac.id/id/eprint/50948 |
Actions (login required)
 |
View Item |