Claim Missing Document
Check
Articles

Found 23 Documents
Search

Application of Data Mining to Predict Student Academic Performance at Universitas Mahakarya Asia Ahmad Budi Trisnawan; Elkin Rilvani
Journal of Intelligent Systems and Information Technology Vol. 3 No. 1 (2026): January
Publisher : Apik Cahaya Ilmu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61971/jisit.v3i1.153

Abstract

Student academic performance is one of the main indicators of the success of the learning process in higher education. Early prediction of academic performance is important to identify students who have the potential to experience academic difficulties so that interventions can be provided in a timely manner. This study aims to apply data mining to predict the academic performance of students of Mahakarya Asia University based on academic and demographic historical data, by comparing two classification algorithms, namely Random Forest and Support Vector Machine (SVM). The prediction results are in the form of academic performance class labels (variable Y) which consist of two classes, namely “On-Time” and “Delayed”, so that the problem is formulated as a binary classification and not a numerical value prediction. The dataset includes the previous semester's GPA, attendance, core course scores, age, gender, and study program. The research stages include data preprocessing, algorithm implementation using Scikit-learn, 80% training data sharing and 20% test data, and evaluation using 10-fold cross-validation. The evaluation results showed that Random Forest obtained an accuracy of 85.2%, accuracy of 84.1%, recall of 82.7%, and an F1-score of 83.4%, higher than SVM with an accuracy of 78.4%, accuracy of 76.9%, recall of 75.2%, and an F1-score of 76.0%. These findings indicate that Random Forest is superior in handling the complexity of diverse academic data. The model built can be used as a tool for Mahakarya University Asia in identifying at-risk students early and supporting academic decision-making.
Analisis Efektivitas Algoritma Komputasi pada Sistem Pendukung Keputusan Ahmad Budi Trisnawan
Telcomatics Vol. 10 No. 1 (2025)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v10i1.11022

Abstract

Decision Support Systems (DSS) play a crucial role in assisting decision-makers by analyzing large and complex datasets to generate actionable insights. The core performance of a DSS relies heavily on the computational algorithms embedded within its structure, which are responsible for data processing, pattern recognition, and prediction. This study aims to evaluate the effectiveness of three commonly used algorithms Decision Tree (C4.5), Naive Bayes, and K-Nearest Neighbor (K-NN) in supporting decision-making processes using healthcare-related data. The analysis focuses on three performance metrics: classification accuracy, computational speed, and memory usage. A benchmark dataset on heart disease from the UCI Machine Learning Repository was utilized for empirical testing. Results indicate that the Decision Tree algorithm achieved the highest accuracy (92%) and interpretability, making it well-suited for transparent decision-making contexts. Naive Bayes demonstrated the fastest processing time and lowest memory consumption, making it ideal for real-time or resource-constrained systems. Meanwhile, K-NN showed moderate performance but was sensitive to parameter tuning and data volume. These findings suggest that algorithm selection should be aligned with system requirements and resource availability. The study contributes to the development of more efficient and tailored decision support systems by providing empirical evidence of algorithmic strengths and limitations across multiple evaluation dimensions.
Digital Infrastructure and Renewable Electricity Profiles in ASEAN: A Data-Driven Comparative Analysis Yassine HADDIOUI; Ahmad Budi Trisnawan; Irwandi Rizki Putra; Mazahir Hussain
Journal of Science, Technology, and Innovation Vol 2 No 2 (2026): : December: Inventa: Journal of Science, Technology, and Innovation
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65310/wg34zw21

Abstract

This study develops a comparative technology–energy profile of ten ASEAN economies using fixed broadband subscriptions, renewable electricity generation, and annual GDP per capita growth. Rather than estimating causal relationships from a small cross-sectional population, the study applies standardized-distance profiling to identify country configurations and examine how digital connectivity, renewable electricity penetration, and short-run economic dynamics coexist. The dataset combines internationally comparable indicators from the International Telecommunication Union, World Bank, Ember, and Our World in Data, using the most recent comparable observations available for 2024–2025. Each indicator is standardized through z-scores, and countries are classified according to their Euclidean distance from analytically defined reference profiles. The results identify three empirical configurations characterized by different combinations of connectivity, renewable electricity, and economic growth. Viet Nam displays relatively strong performance across all three dimensions, while Laos combines very high renewable electricity penetration with limited fixed broadband infrastructure. Singapore and Brunei demonstrate relatively strong connectivity alongside comparatively low renewable electricity shares. The findings indicate that digital infrastructure and energy transition are interconnected but non-equivalent dimensions requiring differentiated comparative analysis.