cover
Contact Name
Mesran
Contact Email
jurnal.josh@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.josh@gmail.com
Editorial Address
Sekretariat Forum Kerjasama Pendidikan Tinggi (FKPT) Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH)
ISSN : -     EISSN : 2686228X     DOI : -
Core Subject : Science,
Artikel yang dimuat melalui proses Blind Review oleh Jurnal JOSH, dengan mempertimbangkan antara lain: terpenuhinya persyaratan baku publikasi jurnal, metodologi riset yang digunakan, dan signifikansi kontribusi hasil riset terhadap pengembangan keilmuan bidang teknologi dan informasi. Fokus Journal of Information System Research (JOSH)
Articles 774 Documents
Prediksi Harga Penutupan Saham Gojek-Tokopedia Menggunakan Model Hybrid GARCH-LSTM Pramudito, Farhan Wegig; Arianto, Kezia Jazzlyn; Thoyib, Najma Humairoh; Arvintyani, Risquina Angelica; Herlambang, Yudhistira Jalu; Zuhdi, Syaifudin
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.8911

Abstract

This study proposes the application of a hybrid GARCH–LSTM model to predict GoTo stock prices in the context of Indonesia's rapidly growing digital economy. GoTo stock prices are characterized by high volatility and a non-linear time series pattern, making them difficult to model using conventional approaches. Daily closing price data from 2022 to November 2025 are transformed into logarithmic returns to meet the stationarity assumption. The GARCH(1,1) model is used to estimate conditional volatility, which represents short-term risk dynamics and the volatility clustering phenomenon. Furthermore, historical returns and conditional volatility are used as additional features in the LSTM model to predict the next period's stock returns, which are then converted back into closing price predictions. The estimation results show that all GARCH parameters are statistically significant, indicating the persistence of volatility in GoTo stock data. Evaluation of the performance of the hybrid model on the test data produces an RMSE value of 3.126, an MAE of 2.245, and a coefficient of determination (R²) of 0.899, indicating that the model is able to represent stock price movement patterns well. These findings indicate that the hybrid GARCH–LSTM approach is effective in modeling stock price dynamics under highly volatile market conditions.
Perancangan Aplikasi Tiket Wisata Air Terjun Berbasis Web Menggunakan Metode Agile Scrum Syarifah, Hafa Leny Tahta; Swastyastu, Cempaka Ananggadipa; Shanty, Ratna Nur Tiara
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.8920

Abstract

The rapid advancement of information technology has become a key driver of digital transformation across various sectors, including tourism. The utilization of technology in managing tourist destinations can enhance service efficiency and improve the quality of information provided to visitors. One of the challenges faced by Dlundung Waterfall Tourism is the ticket booking process, which is still carried out manually, resulting in long queues, data recording errors, and the risk of information loss during data recap. These conditions lead to inefficient data management and hinder efforts to improve service quality for tourists. This study aims to design and develop a web-based ticket booking application for Dlundung Waterfall Tourism to assist administrators in automating service processes. In its development, the Agile Scrum methodology is employed, as it can quickly adapt to changing requirements through iterative stages. Additionally, the Laravel framework is chosen as the primary development foundation because it offers a robust architectural structure, strong security features, and convenience in data management and organized feature development. The application includes several main features, such as the home page, online ticket booking, destination information, payment, my tickets, and contact.
Sistem Lingkungan Pintar Solusi Cerdas Pengelolaan Sampah Menggunakan Adaptasi Machine Learning dan Internet of Things Widiyono, Widiyono; Amalia, Nurul; Ismanto, Bambang
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.8941

Abstract

Indonesia's waste generation increased from 28.59 million tons per year in 2021 to 34.21 million tons per year in 2024, a 19.67% increase. However, in 2024, only 46.1% of the total waste generation was successfully managed.. This condition highlights the need for a more efficient waste management solution, particularly at Temporary Disposal Sites (TPS), which still rely on manual monitoring and often experience waste overflow. This study aims to develop a Smart Environmental System based on the Internet of Things (IoT) and Machine Learning to monitor waste levels in real time and predict disposal patterns using historical data. The research uses a qualitative approach through field observations, interviews with the Environmental Agency, and literature studies to identify system requirements. System design was carried out using UML diagrams, followed by the development of an IoT device using ESP32 and an Android application built with Flutter, integrated with Firebase. The Machine Learning model employs the Random Forest algorithm to classify waste-level conditions. System testing included unit testing, integration testing, performance testing, and user evaluation using the PIECES method. The results show that the Performance, Information, Control, and Efficiency aspects scored above 80%, indicating that the system effectively provides sensor information, ensures data security, and improves operational efficiency. However, the Economic and Service aspects still require optimization, particularly in reducing operational costs and improving system maintenance routines. Overall, the system demonstrates strong potential in supporting smarter, faster, and more efficient waste management, and is suitable for further development.
Pengembangan Aplikasi Notulensi Rapat Berbasis Web Pada Rumah Sakit Menggunakan Motode Waterfall Febri, Febri; Wardani, Muhammad; Astri, Lola Yorita; Surya, Chandy Ophelia; Rofi'i, Imam
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.8953

Abstract

Baiturrahim Hospital in Jambi routinely holds coordination and evaluation meetings as part of its efforts to improve the quality of hospital services and management. However, the process of recording meeting minutes is still done manually using separate documents, resulting in delays in report preparation, difficulties in searching meeting archives, and an increased risk of data loss. This study aims to develop a web-based meeting minutes application that can support the process of recording, storing, and presenting meeting reports in an integrated manner. The software development method used is the Waterfall method, which includes the stages of needs analysis, system design, implementation, testing, and maintenance. Data collection was carried out through workflow observations and interviews with administrative staff and related units at Baiturrahim Hospital in Jambi. The results of functional testing indicate that the application can accelerate the process of creating meeting minutes, improve the ease of searching and managing meeting archives, and assist in monitoring the follow-up of meeting results in a more structured manner. Thus, this web-based meeting minutes application is considered suitable for use as a supporting tool for meeting administration and has the potential to increase the effectiveness and efficiency of meeting management at Baiturrahim Hospital in Jambi.
Sistem Informasi Prediksi Harga Saham Bank Syariah Menggunakan Metode Arima dan Sarima dengan Antarmuka Visual AC, Muhamad Fadhil; Hilda, Atiqah Meutia
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9026

Abstract

Stock price movements are highly dynamic, requiring prediction approaches that are not only accurate but also easy for users to understand. This study focuses on the development of abased stock price prediction information system for Bank Syariah Indonesia Tbk (BRIS) using a time series forecasting approach. The data used consist of historical BRIS stock prices (open, high, low, close, and volume) obtained from Investing.com and processed through data cleaning, normalization, and preparation to meet time series modeling assumptions. The prediction models applied in this study are ARIMA and SARIMA, with parameter selection based on ACF and PACF analysis. Model performance was evaluated using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) to determine the accuracy level of the predictions. The evaluation results indicate that the ARIMA model outperforms the SARIMA model, achieving an MAE of 0,1266, RMSE of 0,1519, while the SARIMA model records an MAE of 0,1811, RMSE of 0,1955. The best model was then integrated into a web-based information system using Flask and React.js, which provides visualization of prediction results through interactive charts and comparisons with actual data. The system displays stock price prediction results in the form of interactive charts alongside actual data comparisons, aiming to help users understand stock price trends and support more objective, data-driven investment decisions.
Design and Implementation of a Captive Portal Login System for Improved Network Security and User Access Management Kesumahadi, Lisdianto Dwi; Anwar, Nuril; Charlos, Feby; Setya, Bagus
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9082

Abstract

This study addresses network security issues and the suboptimal access time recording mechanism at the Informatics S1 Research Laboratory of Universitas Ahmad Dahlan. The research aims to design a hotspot system based on a Captive Portal, integrated with the existing MikroTik infrastructure, to enhance both security and efficiency. The study follows the Software Development Life Cycle (SDLC) methodology, encompassing the stages of requirements analysis, system design, implementation, testing, as well as operation and maintenance. Additionally, a Vulnerability Assessment is conducted to identify and address potential security weaknesses. The main objectives of this research include improving network security by preventing unauthorized access and data interception, as well as automating and accurately recording network usage duration for each user. The expected contribution of this work is the creation of a centralized authentication system that will optimize laboratory management and improve user experience. Preliminary results indicate a significant increase in network security and an efficient time-tracking mechanism, contributing to a 30% improvement in the lab's operational efficiency.
Perancangan Sistem Informasi Pengingat Jadwal Kegiatan Harian Berbasis Mobile Untuk Meningkatkan Manajemen Waktu Alda, Muhamad; Manik, Aprilia Lavigne; Agustina, Sofia; Marpaung, Lisa Fauziah; Adella, Anggun
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9090

Abstract

The rapid development of information technology provides convenience in various aspects of life, but it also creates challenges in time management due to high levels of distraction. Each individual has different daily activities, which require effective schedule management to ensure productivity. This study aims to design a mobile-based daily activity reminder information system to improve users’ time management. The research method used is qualitative, with data collection techniques including literature study and interviews. The system development method applied is the prototype method, which consists of communication, quick plan, modelling, construction, and deployment stages. The results of this study are the design and prototype of a daily activity reminder application equipped with scheduling features and reminder notifications before, during, and after activities. This application is expected to assist users in managing daily activities more systematically and improving awareness of time management.
Peningkatan Akurasi Prediksi Stok Bahan Baku Furnitur Menggunakan Algoritma Random Forest Regressor Berbasis Web Nafi’uzzahidi, Ahmad; Wibowo, Gentur Wahyu Nyipto; Sarwido, Sarwido
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9095

Abstract

This study aims to address the uncertainty of raw material inventory in the furniture industry through the implementation of the Random Forest Regressor machine learning algorithm. The primary problem addressed is demand fluctuation, which frequently leads to stock management inefficiencies, including overstocking or material shortages that disrupt production processes. The research method employs a quantitative approach with an experimental design, developing a web-based system using the Flask framework and MySQL database. The data sample includes historical sales transaction records and Bill of Materials (BOM) data for furniture products, such as dining tables and minimalist chairs. Prior to modeling, the data underwent a preprocessing stage comprising data cleaning, handling missing values, and normalization to minimize the impact of noise on transaction data. Data collection was conducted through the extraction of internal databases, which were then processed through feature engineering stages based on temporal trends. The results demonstrate that the Random Forest model can predict future raw material requirements with high accuracy, evidenced by a coefficient of determination ($R^2$) of 0.84 and a Mean Absolute Error (MAE) of 5.4.5 These findings prove that a data-driven approach provides more precise stock requirement estimations than conventional methods. In conclusion, the integration of this predictive technology offers practical contributions to accelerating managerial decision-making and optimizing operational efficiency in the medium-scale manufacturing sector. The implications of this study support the theoretical development of artificial intelligence-based decision support systems in supply chain management.
Optimalisasi Prediksi Kelulusan Mahasiswa Menggunakan Algoritma Decision Tree CART Abdillah, Afiani Agus; Cahyono, Yono; Desyani, Teti; Rosyani, Perani
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9099

Abstract

Timely student graduation is a key indicator of higher education quality and institutional effectiveness. This study aims to optimize student graduation prediction using a Decision Tree algorithm based on Classification and Regression Tree (CART) by integrating academic and non-academic variables. The dataset used in this study is the open-source Student Graduation Dataset obtained from Kaggle, consisting of 379 student records with graduation status as the target variable. The research stages include data preprocessing through mean imputation for missing values, categorical variable transformation, data splitting with an 80:20 ratio, and model optimization using CART hyperparameter tuning as a form of post-pruning. Model performance was evaluated using accuracy, precision, recall, F1-score, and a confusion matrix. The experimental results show that the optimized CART model achieved an accuracy of 92.1%, with F1-scores above 0.90 for both graduation classes and a balanced trade-off between precision and recall. Furthermore, the resulting decision tree structure is relatively simple and highly interpretable. These findings indicate that the optimized CART algorithm is effective and suitable for implementation as an early warning system to support academic decision-making in higher education institutions.
Klasifikasi Batu Permata Berbasis Citra Menggunakan Convolutional Neural Network Rosyani, Perani; Hariansyah, Oke; Permadi, Yuda; Rosdiana, Muhamad; Nanang, Nanang
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9101

Abstract

Manual gemstone identification still faces several limitations, such as subjective assessment and strong dependence on expert experience, which may lead to misclassification, particularly for gemstones with similar visual characteristics. This study aims to apply a Convolutional Neural Network (CNN) for automatic visual-based gemstone image classification using a limited dataset. The dataset consists of three gemstone classes, namely Alexandrite, Almandine, and Amazonite, with a balanced class distribution. Image preprocessing includes image resizing, pixel value normalization, and data augmentation to increase data variability. The proposed CNN model is a custom architecture composed of three convolutional layers with ReLU activation, followed by max pooling, a fully connected layer with dropout, and a Softmax output layer. Model performance is evaluated using a confusion matrix and classification metrics, including accuracy, precision, recall, and F1-score. Experimental results show that the CNN model achieves a testing accuracy of 93.33% on the limited test dataset with relatively balanced performance across classes. However, analysis of the training and validation curves indicates the presence of overfitting, suggesting that the model’s generalization capability to unseen data remains limited. These findings highlight that the achieved accuracy is conditional on the specific and constrained dataset used. Therefore, future work is recommended to expand dataset size and diversity, apply more comprehensive data augmentation strategies, and explore transfer learning approaches to improve model stability and generalization performance.