Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Journal of Information Systems and Informatics International Journal Software Engineering and Computer Science (IJSECS)
Lili Dwi Yulianto
Nasional University
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Feature Selection vs Dimensionality Reduction for Steam Game Metadata Classification: An Ensemble Learning Study Ferdi Setyo Handika; Lili Dwi Yulianto; Septi Andryana
Journal of Information System and Informatics Vol 8 No 1 (2026): February
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i1.1456

Abstract

Optimizing noisy Steam game metadata is essential for accurate binary classification. This study compares feature selection (MI) and dimensionality reduction (PCA, LDA) using a dataset of 55,144 Steam reviews and four ensemble algorithms, evaluated through Stratified 5-Fold Cross-Validation. The results show that the 125-feature baseline achieved the highest accuracy of 0.7728 with CatBoost. Feature selection (FS_10) maintained competitive performance with an accuracy of 0.7449, while LDA, after optimization, achieved 0.7281. In contrast, PCA significantly hindered performance (0.6963) due to the inability of linear transformations to preserve the discriminative power of one-hot encoded categorical features, which ensemble models handle better in their original form. These findings highlight the importance of preserving original features, especially in low-to-medium dimensional metadata, where feature selection outperforms dimensionality reduction in maintaining predictive integrity. High accuracy is crucial for developers to track product reception and for platforms to improve recommendation systems that influence user purchasing decisions. The study concludes that for Steam game metadata, strategic feature selection is superior to dimensionality reduction for maintaining classification performance.
A Random Forest-Based AI Decision Support System for an Integrated Indonesian Civil Service Information System Virda Mega Ayu; Harianto Harianto; Ali Ahmad; Lili Dwi Yulianto
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.7548

Abstract

Digital transformation in public administration increases the need for personnel information systems that can consolidate fragmented civil-service records and turn them into timely, transparent, and actionable decision support. This study developed SIPINTAR (Integrated, Adaptive, and Responsive Interactive Personnel Intelligence System), an artificial intelligence-based platform designed to integrate civil-service personnel information and support administrative decision-making within an Indonesian government institution. The study adopted a Research and Development approach and implemented the system through a Waterfall-based Software Development Life Cycle. Personnel data from multiple source systems, representing 5,320 civil servants and more than 42,000 historical records for 2019–2025, were integrated using Application Programming Interfaces (APIs) and Extract, Transform, and Load (ETL) processes. The integrated data were then subjected to cleaning, transformation, feature engineering, and Random Forest modeling. Model performance was assessed using accuracy, precision, recall, and F1-score, whereas system acceptance was examined through a User Acceptance Test. The strongest reported result was obtained for employee-performance prediction, with 87.24% accuracy, 86% precision, 85% recall, and 85.5% F1-score. Feature-importance analysis as the explainable artificial intelligence component identified performance score, competency level, and years of service as the three most influential variables. The integrated dashboard and AI Assistant provided consolidated access to analytical information, and the UAT result reached 91.40%. Overall, the findings suggest that SIPINTAR can move personnel information management beyond historical record keeping toward predictive and explainable decision support. Nevertheless, the results should be validated with baseline models and broader institutional datasets before being generalized across agencies.
Co-Authors Ali Ahmad Ferdi Setyo Handika Harianto Harianto Septi Andryana Virda Mega Ayu