Welasih, Rusti Dewi (2026) SISTEM PREDIKSI KELAYAKAN SISWA UNTUK PROGRAM SKS 2 TAHUN MENGGUNAKAN RANDOM FOREST BERBASIS WEBSITE (Studi Kasus pada MAN 1 Kabupaten Ngawi). S1 thesis, Universitas PGRI Madiun.
![[img]](https://eprint.unipma.ac.id/style/images/fileicons/text.png) |
Text
Halaman Depan (Cover - Daftar Isi Lampiran).pdf Download (3MB) |
|
Text
Abstrak.pdf Download (284kB) |
|
Text
BAB I.pdf Download (220kB) |
|
Text
BAB II.pdf Download (767kB) |
|
Text
BAB III.pdf Restricted to Repository staff only Download (363kB) |
|
Text
BAB IV.pdf Restricted to Repository staff only Download (2MB) |
|
Text
BAB V.pdf Download (190kB) |
|
Text
Daftar Pustaka.pdf Download (243kB) |
|
Text
Lampiran.pdf Restricted to Repository staff only Download (1MB) |
Abstract
The Two-Year Semester Credit System program provides students with the opportunity to complete their education in a shorter period according to their academic abilities. However, the process of determining students' eligibility for the program is still carried out conventionally. Therefore, a system is needed to assist schools in predicting student eligibility more efficiently. This study aims to design and implement a web-based student eligibility prediction system for the Two-Year Semester Credit System program using the Random Forest algorithm at MAN 1 Ngawi Regency. The system was developed using the Laravel framework as the user interface, Flask as the API service, and MySQL as the database. The prediction model was developed using the Python programming language with the Random Forest algorithm. Model evaluation was conducted using 5-Fold Cross Validation, Confusion Matrix, and ROC-AUC, while system evaluation was performed using Black Box Testing and the System Usability Scale (SUS). The results showed that all 54 Black Box Testing scenarios were successfully validated. The Random Forest model achieved an average accuracy of 99.12% in the 5-Fold Cross Validation. The Confusion Matrix results showed that the model correctly classified 23 ineligible students and 22 eligible students, with only one misclassification. Furthermore, the model achieved an ROC-AUC value of 0.9962, resulting in an optimal decision threshold of 0.6935. In addition, the SUS evaluation produced a score of 79.5, which falls into the Acceptable, Grade B, and Good categories. Based on these results, the developed system is capable of accurately predicting students' eligibility for the Two-Year Semester Credit System program and demonstrates good usability, making it suitable to support school decision-making.
| Item Type: | Thesis/Skripsi/Tugas Akhir (S1) |
|---|---|
| Kata Kunci: | Kata kunci : Random Forest, Prediksi Kelayakan Siswa, Sistem Kredit Semester, Website. Keywords : Random Forest, Student Eligibility Prediction, Semester Credit System, Website. |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Teknik > Teknik Informatika |
| Depositing User: | WELASIH DEWI RUSTI |
| Date Deposited: | 30 Jul 2026 06:22 |
| Last Modified: | 30 Jul 2026 06:22 |
| URI: | http://eprint.unipma.ac.id/id/eprint/8125 |
Actions (login required)
 |
View Item |
