PENGEMBANGAN WEBSITE JUARA SEMERCU MENGGUNAKAN METODE AGILE DENGAN INTEGRASI ALGORITMA XGBOOST UNTUK PREDIKSI CAPAIAN PRESTASI MAHASISWA

PARDEDE, YOSUA EBENEZER (2026) PENGEMBANGAN WEBSITE JUARA SEMERCU MENGGUNAKAN METODE AGILE DENGAN INTEGRASI ALGORITMA XGBOOST UNTUK PREDIKSI CAPAIAN PRESTASI MAHASISWA. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 COVER.pdf Download (349kB) | Preview
	Text (BAB I) 02 BAB 01.pdf Restricted to Registered users only Download (39kB)
	Text (BAB II) 03 BAB 02.pdf Restricted to Registered users only Download (284kB)
	Text (BAB III) 04 BAB 03.pdf Restricted to Registered users only Download (182kB)
	Text (BAB IV) 05 BAB 04.pdf Restricted to Registered users only Download (1MB)
	Text (BAB V) 06 BAB 05.pdf Restricted to Registered users only Download (30kB)
	Text (DAFTAR PUSTAKA) 07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (147kB)
	Text (LAMPIRAN) 08 LAMPIRAN.pdf Restricted to Registered users only Download (324kB)

Abstract

The management of student achievement data at Mercu Buana University is currently conducted conventionally, decentralized, and heavily relies on physical document recapitulation. This situation leads to slow bureaucratic validation workflows and difficulties in mapping achievement trends to support institutional accreditation reporting (SIMKATMAWA). Therefore, this research aims to develop a web-based management information system named "Juara Semercu" while integrating a predictive model to project future achievement trends. The software development was conducted using the Agile methodology, utilizing Next.js, Express.js, and a PostgreSQL database. To address the need for predictive analytics, the Extreme Gradient Boosting (XGBoost) Regression algorithm was implemented using a time-series feature engineering approach. Based on User Acceptance Testing (UAT) and functional system evaluations, the application successfully digitized the document submission workflow by accommodating four levels of access rights (Student Affairs Bureau, Rectorate, Study Program Administration, and Student Activity Units). In the machine learning evaluation phase, the XGBoost model proved capable of accurately learning the historical patterns of student achievement data and predicting subsequent trends with minimal error, as evidenced by the optimal measurement results of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-Squared (R2) metrics. In conclusion, the integration of this information system and predictive algorithm successfully provides bureaucratic transparency and serves as a strategic foundation for university leadership in planning student coaching programs. Keywords: Achievement Management, Agile, Information System, Time-Series Prediction, XGBoost. Pengelolaan data capaian prestasi mahasiswa di Universitas Mercu Buana saat ini masih berjalan secara konvensional, belum terpusat, dan sangat bergantung pada rekapitulasi dokumen fisik. Hal ini menyebabkan lambatnya alur validasi birokrasi dan sulitnya pemetaan tren prestasi guna menunjang pelaporan akreditasi institusi (SIMKATMAWA). Oleh karena itu, penelitian ini bertujuan untuk mengembangkan sistem informasi manajemen "Juara Semercu" berbasis website sekaligus mengintegrasikan model prediktif untuk memproyeksikan tren capaian prestasi di masa mendatang. Pengembangan perangkat lunak dilakukan menggunakan metode Agile dengan memanfaatkan kerangka kerja Next.js, Express.js, dan basis data PostgreSQL. Untuk menjawab kebutuhan analitik prediktif, diimplementasikan algoritma Extreme Gradient Boosting (XGBoost) Regression menggunakan pendekatan time-series feature engineering. Berdasarkan hasil User Acceptance Test (UAT) dan pengujian fungsional sistem, aplikasi ini berhasil mendigitalisasi alur pengajuan dokumen dengan mengakomodasi empat tingkatan hak akses (Biro Kemahasiswaan, Rektorat, Tata Usaha Program Studi, dan Unit Kegiatan Mahasiswa). Pada tahap evaluasi machine learning, model XGBoost terbukti mampu mempelajari pola historis data prestasi mahasiswa secara akurat dan memprediksi tren capaian berikutnya dengan tingkat kesalahan yang minim, dibuktikan oleh hasil pengukuran evaluasi metrik Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), dan nilai R-Squared (R2) yang optimal. Kesimpulannya, integrasi antara sistem informasi dan algoritma prediktif ini berhasil menghadirkan transparansi birokrasi serta dapat menjadi landasan strategis bagi pimpinan universitas dalam merencanakan program pembinaan mahasiswa. Kata Kunci: Agile, Manajemen Prestasi, Prediksi Deret Waktu, Sistem Informasi, XGBoost

Item Type:	Thesis (S1)
NIM/NIDN Creators:	41522010193
Uncontrolled Keywords:	Agile, Manajemen Prestasi, Prediksi Deret Waktu, Sistem Informasi, XGBoost
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.7 Multimedia Systems/Sistem-sistem Multimedia > 006.75 Social Multimedia/Multimedia Social > 006.752 Blogs/Blog, Web Blog 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik > 518.1 Algorithms/Algoritma
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	khalimah
Date Deposited:	14 Sep 2026 09:34
Last Modified:	14 Sep 2026 09:34
URI:	http://repository.mercubuana.ac.id/id/eprint/103864

Actions (login required)

View Item