Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Mujibul Hakim
Universitas Stikubank Semarang
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
SEGMENTASI PROBABILISTIK CALON MAHASISWA BERBASIS INDOBERT, GAUSSIAN MIXTURE MODEL, DAN LLM DI ITSNU PEKALONGAN Mujibul Hakim; Eri Zuliarso
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8370

Abstract

Private higher education institutions face challenges in understanding shifting prospective-student characteristics driven by socio-economic dynamics, including the COVID-19 pandemic. ITSNU Pekalongan recorded a non-linear enrollment pattern in 2019–2024 (from 146 to a peak of 680; N = 2,362). This study aims to analyze probabilistic segmentation, measure cross-period structural breaks, build an LLM-based analysis automation system, and validate it through expert judgement. A Research and Development approach follows a ten-stage CRISP-DM framework: IndoBERT (768 dimensions), PCA, Gaussian Mixture Model (GMM) with diag covariance and k-means++ init, Adjusted Rand Index (ARI), and a Hybrid Cognitive Pipeline (local Llama 3.2 and OpenRouter cloud). The results show that 4 of 5 inter-period transitions are structural breaks (ARI < 0.30), identical-entity cosine similarity of IndoBERT embeddings averages 0.9234 (range 0.8932–0.9426), and expert validation reaches 4.0/5.0 for a 2025 projection of 592 applicants. The IndoBERT–GMM–LLM integration yields a replicable recruitment decision-support system.
Co-Authors Eri Zuliarso