p-Index From 2021 - 2026
3.323
P-Index
Claim Missing Document
Check
Articles

Principal Component Analysis and Bacterial Foraging Optimization for Credit Scoring Arjun, Jennifer; Kisworo, Marsudi Wahyu; Negara, Edi Surya; Ependi, Usman
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 1 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i1.2515

Abstract

Information technology in the current era is developing very quickly. Information systems themselves are found in various aspects of life, such as health, law, education and finance. With the improvement of information systems, systems can be created as considerations for making decisions or agreements. Credit scoring is a status that is usually held by banks or other financial institutions and contains data from debtors who have applied for credit at certain banks or financial institutions. There are many attributes in determining whether someone will get good credit or bad credit status. Therefore, a fast and accurate classification method is needed. This research proposes the use of Principal Component Analysis to reduce several attributes without reducing the attributes that are important or crucial in determining. This research also uses the Bacterial Foraging Optimization algorithm to optimize qualification results on the Support Vector Machine which uses 4 kernels, namely Linear, RBF, Polynomial and Sigmoid. The research results show that the Linear kernel accuracy which only uses Principal Component Analysis gets a value of 79%. Then optimized with Bacterial Foraging Optimization to get an accuracy of 81%. So the Bacterial Foraging Optimization algorithm increases accuracy by 2%. For RBF and Poly kernels, the accuracy is the same, namely 78%. For the Sigmoid kernel, it got the best results in Principal Component Analysis, namely getting an accuracy value of 80%.
A Novel Hybrid Classification on Urban Opinion Using ROS-RF: A Machine Learning Approach Ependi, Usman; Ahmad, Nahdatul Akma
Jurnal Penelitian Pendidikan IPA Vol 10 No 8 (2024): August
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v10i8.8042

Abstract

Urban opinion from crowdsourced data often leads to imbalanced datasets due to the diversity of issues related to urban social, economic, and environmental topics. This study presents a novel hybrid approach that combines Random Over-Sampling and Random Forest (ROS-RF) to effectively classify such imbalanced data. Using crowdsourced urban opinion data from Jakarta, experimental results show that the ROS-RF method outperforms other approaches. The ROS-RF classifier achieved an impressive F1-score, recall, precision, and accuracy of 98%. These findings highlight the superior effectiveness of the ROS-RF method in classifying urban opinions, especially those related to social, economic, and environmental issues in urban settings. This hybrid approach provides a robust solution for managing imbalanced datasets, ensuring more accurate and reliable classification outcomes. The study underscores the potential of ROS-RF in enhancing urban data analysis and decision-making processes
Predicting Bitcoin and Ethereum Prices Using the Long Short- Term Memory (LSTM) Model Aswadi, M; Ependi, Usman
Journal of Information System and Informatics Vol 7 No 3 (2025): September
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i3.1228

Abstract

Cryptocurrency is a highly volatile digital asset, necessitating accurate and adaptive forecasting methods. This study implements a Long Short-Term Memory (LSTM) model to predict the daily closing prices of two leading cryptocurrencies Bitcoin (BTC) and Ethereum (ETH) using historical data from Yahoo Finance and Binance. To enhance data richness and model robustness, datasets from both sources were vertically merged. The methodological framework included data preprocessing, Min–Max normalization, formation of 24-day sliding input windows, and training across three data split ratios (70:30, 80:20, and 90:10). Model performance was evaluated using the Root Mean Squared Error (RMSE). Results indicate that the LSTM model achieved high prediction accuracy, with the lowest RMSE values of 0.0137 for BTC and 0.0152 for ETH using the combined dataset with a 90:10 split. Beyond modeling, a web-based application was developed using Streamlit, enabling users to perform real-time predictions and export results. This study contributes to the field of cryptocurrency forecasting by demonstrating that multi-source data integration significantly improves predictive accuracy and model generalization. The proposed framework offers both theoretical insights and practical tools for researchers and investors in financial technology.
Predicting Accounts Receivable of the Social Security Administration for Employment Using LSTM Algorithm Khansa, Ainna; Ependi, Usman
Journal of Information System and Informatics Vol 7 No 4 (2025): December
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v7i4.1274

Abstract

This study explores the use of Long Short-Term Memory (LSTM) networks for predicting outstanding contributions from employers to the BPJS Ketenagakerjaan, Indonesia’s social security agency. The research aims to address the challenges BPJS faces due to delayed or unpaid contributions, which impact the institution's operational stability and financial health. The LSTM model, a deep learning technique well-suited for time-series prediction, was applied to historical data from BPJS Ketenagakerjaan to predict overdue contributions across three different training-validation splits: 70:30, 80:20, and 90:10. The results demonstrate that the 80:20 split achieved the highest validation accuracy of 84.71%, offering the optimal balance between training data and model generalization. The model's ability to predict overdue contributions with high accuracy could significantly improve BPJS's receivables management, allowing for more proactive financial planning and risk mitigation. The study also highlights the integration of an attention mechanism within the LSTM model, enhancing its predictive capabilities by focusing on the most relevant historical data. This research contributes to the field of predictive analytics in public sector financial management, showcasing the potential of machine learning in enhancing the efficiency and effectiveness of social security programs.
DIGITALISASI LAYANAN KOPERASI SAWIT BERBASIS WEB-MOBILE: STUDI PKM DI KOPERASI JAYA SEMPURNA, PALI Ependi, Usman; Aliya, Sabeli; Irawan, Dedi
Jurnal Abdi Insani Vol 12 No 12 (2025): Jurnal Abdi Insani
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/abdiinsani.v12i12.3104

Abstract

The main issues faced by the target partner are the limited access to technical information regarding oil palm cultivation and the inefficiency of manual data management in the cooperative. To address these issues, the program proposes a solution in the form of the development of the Agrisawit application (for farmers) and the Cooperative Dashboard (for cooperative managers), both web and mobile-based, which is expected to facilitate farmers in accessing information related to oil palm cultivation, as well as making it easier for cooperative managers to manage data and communicate with members. The main objective of this community service program is to improve the operational efficiency and productivity of oil palm farmers at Koperasi Jaya Sempurna, Desa Pengabuan, Kecamatan Abab, Kabupaten PALI, South Sumatra Province, through the implementation of a digital-based information system. The program also includes digital literacy training for cooperative managers and members. Evaluation results show an 80% increase in application usage, a productivity increase in oil palm ranging from 45-90%, and a 90% improvement in the operational efficiency of the cooperative. This program is expected to have a sustainable positive impact on the cooperative and its members, and to serve as a model for the development of technology-based agribusiness in rural areas.
Oil and Gas Production Forecasting Based on LSTM Model: A Case Study of PT Pertamina Hulu Rokan Zone 4 Billan, Angel Caroline; Ependi, Usman
Journal of Information System and Informatics Vol 7 No 4 (2025): December
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v7i4.1285

Abstract

This study addresses the critical need for accurate oil and gas production forecasting to support strategic decision-making in Indonesia’s energy sector. PT Pertamina Hulu Rokan Zone 4 (PHR Zona 4), a key player in national energy production, frequently encounters technical and external operational challenges. To tackle these issues, this research proposes a deep learning-based predictive model using the Long Short-Term Memory (LSTM) architecture, structured in an encoder-decoder format and enhanced with an attention mechanism. The model was trained and tested on historical oil and gas production data from PHR Zona 4, evaluated under two data-splitting scenarios: 80:20 and 90:10. Model performance was assessed using Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). Results from the 80:20 scenario showed RMSE of 5.83, MAE of 5.54, MAPE of 1.71%, and R² of -1.97, suggesting difficulties in capturing extreme data fluctuations. However, the 90:10 scenario demonstrated significantly improved performance with RMSE of 0.42, MAE of 0.36, MAPE of 0.11%, and R² of 0.00, indicating better trend prediction stability. The novelty of this study lies in the integration of attention mechanisms within the LSTM encoder-decoder framework for oil and gas time series forecasting, offering enhanced accuracy and robustness. This research provides a valuable foundation for future improvements in predictive analytics and operational efficiency in the oil and gas industry.
Pengujian Usability dengan Teknik System Usability Scale pada Test Engine Try Out Sertifikasi Suyanto Suyanto; Usman Ependi
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 19 No. 1 (2019)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v19i1.503

Abstract

Test engine try out is an information system used by prospective alumni students to practice the questions in taking the certification exams at Bina Darma University. Exercises that can be done on this test engine are vendor certifications such as Microsoft Technology Associate, SAP, NIIT, PASAS, CISCO, and various other certifications. To ascertain whether the test engine is in line with the expectations and needs of the participants try out then an evaluation is carried out. The evaluation technique used is usability with the system usability scale approach. System usability scale is an information system evaluation technique that looks at three aspects, namely adjective rating, grade scale, acceptability by involving end users in the evaluation process. In the process of evaluating the usability scale system, ten instruments were used as a measure of evaluation. From the evaluation, the final result is 87.33. According to these conditions, it can be concluded that the test engine try out from the side of the adjective rating includes the excellence group, from the grade scale side including B group, and from the acceptability side including the acceptable group.
Artificial intelligence in education: a bibliometric analysis of emerging trends Seong Pek, Lim; Akma Ahmad, Nahdatul; Zulkifli, Faiz; Syamilah Che Yob, Fatin; Ependi, Usman; Rhoel C. Cruz, Geoffrey
International Journal of Evaluation and Research in Education (IJERE) Vol 15, No 1: February 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijere.v15i1.34428

Abstract

This study investigates the transformative potential of artificial intelligence (AI) in education through a bibliometric analysis of 291 scholarly works retrieved from the Web of Science (WoS) database. Traditional methods of instruction are under threat from the growing demand for individualized and equitable education, particularly in underserved communities. This study looks at how AI innovations, like virtual assistants and adaptive learning platforms, can enhance learning outcomes and the efficacy of instruction in order to address these concerns. The methodology used co-occurrence and co-citation analyses to map research trends and find educational and AI thematic clusters. Pedagogical frameworks, medical education innovations, ethical governance, generative AI applications, and AI acceptance are the five main research areas highlighted in the findings. With 5,246 citations and an H-index of 42, the data show how widely used AI is in both academia and industry. Adaptive learning models, moral dilemmas, and AI literacy are emerging themes. According to this research, AI has the potential to improve accessibility, equity, and quality in education while tackling issues like algorithmic bias and digital divides. This is in line with sustainable development goal 4 (quality education). Teachers, legislators, and technologists can use this study’s thorough intellectual landscape to gain practical insights on how to responsibly incorporate AI into educational systems for more sustainable innovation.