Aan Widianto
Universitas Mercu Buana Yogyakarta

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

Found 1 Documents
Search

DISTROMATCH: SISTEM REKOMENDASI DISTRIBUSI LINUX DENGAN TOPSIS, BAYESIAN SHRINKAGE, DAN SOFT CONSTRAINT Aan Widianto; Agus Sidiq Purnomo
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.v11i2.8190

Abstract

The diverse Linux ecosystem complicates the selection of suitable distributions for users, particularly beginners. This study develops Distromatch, a web-based Decision Support System recommending from 30 Linux distributions using TOPSIS, enhanced with Bayesian shrinkage adjustment and user-level preference penalty as a soft constraint mechanism. Its five-stage pipeline includes criteria weight normalization from user questionnaires, TOPSIS calculation, Bayesian shrinkage, user-level preference penalty, and final ranking. Functional testing confirmed system operation, and domain expert validation for three user profiles (beginner, intermediate, advanced) showed contextually valid Top-5 recommendations, consistent with the Linux ecosystem. Bayesian shrinkage proved to be effective reduced bias for distributions with limited reviews, while soft constraints ensured level-mismatched distributions appeared in rankings with reduced scores. Calculation transparency is provided via an audit page.