International Journal of Advances in Data and Information System
Not a member yet
161 research outputs found
Sort by
Enhancing Student Collaboration in Academic Projects Through a Content-Based Filtering Recommender System
Full text linkThe Informatics Engineering Study Program at UIN Maulana Malik Ibrahim Malang facilitates students in developing their interests and talents through 10 academic communities that serve as forums for knowledge exchange and innovation in IT project development. However, a challenge arises in assigning suitable students to appropriate projects, resulting in many projects being completed by a limited set of students. To address this, a recommender system for academic project members was developed using the Content-Based Filtering method. This system assists project initiators in selecting competent team members based on students’ prior experiences, considering the similarity between project requirements and student profiles. A dataset of 198 student-completed projects was used, with preprocessing, TF-IDF, and cosine similarity applied in the recommendation process. The system was implemented using the Flask framework with Python and HTML. Evaluation was conducted using the SUS method for usability (achieving a score of 79, categorized as excellent) and MAP for model performance across three scenarios. Scenario one (random community) scored 0.92, scenario two (same community) scored 0.79, and scenario three (comparison with actual members) scored 0.98. The results indicate that broader search scopes yield more accurate recommendations. This research contributes to the improvement of collaborative IT project in academic environments by enabling data-driven student member selection. The proposed system has the potential to be adopted by other academic institutions facing similar team formation challenges
Predicting Software Defects at Package Level in Java Project Using Stacking of Ensemble Learning Approach
Full text linkCompared to manual and automated testing, AI-driven testing provides a more intelligent approach by enabling earlier prediction of software defects and improving testing efficiency. This research focuses on predicting software defects by analyzing CK software metrics using classification algorithms. A total of 8924 data points were collected from five open-source Java projects on GitHub. Due to class imbalance, undersampling was applied during preprocessing along with data cleaning and normalization. The final dataset consists of 1314 instances (746 clean and 568 buggy). The predictive model is developed in two stages: base learner (level-0) using AdaBoost, Random Forest (RF), Extra Trees (ET), Gradient Boosting (GB), Histogram-based Gradient Boosting (HGB), XGBoost (XGB), and CatBoost (CAT) algorithms, and meta-learner (level-1) that optimizes the results using ensemble stacking techniques. The stacking model achieved an ROC-AUC score of 0.8575, outperforming all individual classifiers and effectively distinguishing defective from non-defective software components. The comparison of performance improvements between the base model (tree-based ensemble) and stacking was statistically validated using paired t-tests. All p-values were below 0.05, confirming the significance of Stacking’s superior performance, with the largest gain observed against Gradient Boosting (+0.0411, p = 0.0030). The confusion matrix of stacking model is the most optimal model because it has high of True Positive and True Negative, while False Positive and False Negative values are relatively low. These findings affirm that ensemble stacking yields a more robust and balanced classification system, enhancing defect prediction accuracy and enabling earlier issue detection in the Software Development Life Cycle (SDLC).
Analysis Of Healthcare Employees Acceptance Of Digital Transformation In Inpatient Department Electronic Medical Record (EMR) Application At Private Hospital In Tangerang
Full text linkThis study examines the acceptance of healthcare professionals toward digital transformation through the implementation of Electronic Medical Records (EMR) in the inpatient department (IPD) at a private hospital in Tangerang. The research applies a combined analytical model of the Unified Theory of Acceptance and Use of Technology 2 (UTAUT-2) and the Technology Acceptance Model (TAM). A total of 160 doctors, including specialists, formed the study population, with 115 respondents selected as samples. The findings indicate that healthcare professionals generally feel comfortable using the EMR system and have integrated it into their daily practice, although improvements in active utilization and system optimization are still required. Statistical analysis shows that Performance Expectancy, Effort Expectancy, System Quality, and Facilitating Conditions significantly influence Intention to Use, while Habit has no significant effect. Moreover, Intention to Use strongly impacts Use Behavior. These results highlight that enhancing system reliability, usability, and organizational support is essential to increase healthcare professionals’ adoption and behavioral use of EMR in the inpatient department of private hospitals in Tangerang
Blockchain Technology Adoption for Life Insurance: Risk, Readiness, and Relevance
Full text linkBlockchain technology has been widely discussed as a transformative solution for operational inefficiencies in the insurance sector, particularly in automating claims processing, enhancing transparency, and ensuring data immutability. However, adoption within the life insurance industry remains limited. This paper investigates the barriers and potential of blockchain implementation in life insurance through a mapping analysis using the People–Process–Technology (PPT) framework into risk, readiness, and relevance. The research identifies strategic misalignment with existing revenue models, regulatory compliance frictions, and organizational readiness gaps as key obstacles. A five-year cost comparison indicates that while blockchain incurs higher initial investment, it delivers lower operational costs in the long run—particularly in high-volume, deterministic insurance products. Architectural comparisons further highlight the operational advantages and integration challenges of blockchain-based systems over traditional IT infrastructures. The study concludes that although blockchain holds significant promise, its adoption depends on targeted use case selection, organizational transformation, and regulatory alignment
Passenger and Revenue Estimation for New Rail Transit Lines Under Construction: A Demographic Approach
Full text linkThis study proposes a data-driven approach to estimate passenger volume and revenue for new rail transit lines under construction, addressing the challenge of limited historical data. Principal Component Analysis (PCA) was used to reduce 29 demographic variables into three principal components, which collectively captured up to 85% of the variance. These components informed a Fuzzy C-Means (FCM) clustering process that grouped new stations with existing ones based on demographic similarity. The clustering yielded a Fuzzy Partition Coefficient (FPC) of 0.913, indicating high cluster validity and low overlap between clusters. Transition probabilities of passenger flows between stations were modeled using Markov Chains. The expanded transition matrix, incorporating new stations through demographic analogy, demonstrated rapid convergence to a stationary distribution within 5–10 iterations, validating the model’s stability. Simulation results project a 57% increase in weekday passengers and a 74% increase in weekend passengers, with estimated daily revenue peaking at Rp1.216 billion. The evaluation results confirm the robustness and reliability of the combined FCM–Markov model for long-term passenger and revenue forecasting in new transit infrastructure planning
Analysis of Helpdesk System Development in A Manufacturing Company using Design Thinking Approach
Full text linkThe IT department is vital in manufacturing companies, including PT XYZ, where operations involve transforming raw materials into finished goods. With the complexity of these activities, IT support is essential for managing software and hardware that aligns with business processes. PT XYZ implemented a helpdesk system to streamline IT services but encountered communication issues in the ticketing feature, affecting system efficiency and effectiveness. This research aimed to improve communication between users and administrators to enhance efficiency in monitoring and maintaining IT infrastructure. The study used a design thinking approach, chosen for its collaborative, flexible, and adaptive nature. The process began with the empathize stage, using usability scales and in-depth interviews with users to identify pain points and gather insights. Define, ideate, and prototype stages involved brainstorming and designing solutions in collaboration with the IT team. Finally, the testing stage evaluated user feedback on the improved system. The redevelopment of the helpdesk system yielded significant results, including a 12.27-point increase in usability scale scores. Enhanced features addressed user needs effectively, and all components of the upgraded system were well-received during testing. The improvements led to more structured and systematic communication, making the helpdesk system at PT XYZ more effective and efficient
Sentiment Analysis of Twitter Towards the Free Lunch Program Using the C4.5 Algorithm
Full text linkThis study analyzes public sentiment towards the Makan Siang Gratis (Free Lunch) Program on social media X using the C4.5 algorithm. This program, which was initiated as a campaign promise in the 2024 Election, aims to provide free nutritious food for school students in Indonesia. Given the high public interaction on social media, this study was conducted to determine the public response to the program, which can be positive, neutral, or negative sentiment. The methods used include data collection from social media X, text pre-processing, sentiment labeling, application of Term Frequency-Inverse Document Frequency (TF-IDF), and model evaluation with accuracy metrics. The dataset consists of 3,344 tweets which are then classified using the C4.5 algorithm. Based on the evaluation results, it produces an average precision value of 79%, recall of 76%, F1-score of 77%, and is able to provide an accuracy of 78%. Thus, this model shows effective performance in classifying public sentiment. This study can contribute to the use of social media sentiment analysis as a tool for public policy evaluation
Web-Based E-Procurement Development in Regional-Owned Enterprises (BUMD): An R&D Approach
Full text linkThis study presents the design, development, and evaluation of a web-based e-procurement system tailored to the institutional needs of a Regional-Owned Enterprise (BUMD), with a case implementation at PDAM Tirta Kahuripan. Employing a Research and Development (R&D) methodology and assessed using ISO/IEC 25010 standards, the system integrates six core procurement modules—e-Planning, e-Budgeting, e-Preparation, e-Sourcing, e-Contracting, and e-Inventory—alongside a Vendor Management System (VMS) to enhance procurement transparency and supplier accountability. System testing involved both quantitative and qualitative assessments. Functionality and reliability achieved perfect scores (100%), usability scored 79 based on a System Usability Scale (SUS) survey completed by 20 procurement personnel, and maintainability recorded a moderate index of 82.85 based on PHP Metrics analysis. Efficiency testing using GTMetrix resulted in a Grade C, indicating areas for performance optimization. These findings demonstrate that the system is both technically robust and operationally relevant, offering a replicable model for digital procurement reform in decentralized public institutions. The study contributes to interdisciplinary knowledge across software engineering, public sector management, and procurement governance, with implications for future integration, scalability, and policy adoption in similar institutional contexts
Integrating Satellite Imagery and Multicriteria Decision Analysis for High-Resolution Flood Vulnerability Mapping: A Case Study of Jakarta, Indonesia
Full text linkJakarta, Indonesia, ranks among the most flood-prone megacities in the world, with hydrometeorological factors placing up to 98% of its area at flood risk. Its population density—approximately 15,900 individuals per square kilometer—compounds the impacts of flooding through intensified exposure and socio-economic vulnerability. This study presents a novel, data-driven methodology for flood vulnerability assessment in the Jakarta Special Capital Region (DKI Jakarta), integrating satellite remote sensing and geospatial analysis with a Multicriteria Decision Analysis (MCDA) framework. Employing the Analytical Hierarchy Process (AHP) to systematically weight environmental and socio-economic criteria, a Flood Vulnerability Index (FVI) was developed and spatially modeled at a 500-meter grid resolution. The resulting FVI map categorizes vulnerability into five levels: very low, low, moderate, high, and very high. Findings indicate an index range between 0.36 and 0.70, highlighting predominantly moderate to high vulnerability zones across the region. This high-resolution assessment provides actionable insights for disaster risk reduction, urban resilience planning, and targeted policy interventions to mitigate flood-related hazards in Jakarta
Decentralized Electronic Health Record Management with Semantic-Aware Hierarchical Encryption
Full text linkThe rising incidence of cyberattacks targeting electronic health records (EHR) in Indonesia necessitates a robust and context-aware data protection scheme. This paper proposes a decentralised EHR management system that leverages blockchain, IPFS, and a novel Semantic-Aware Hierarchical Encryption (SAHE) algorithm. SAHE enables multi-level access control based on data sensitivity semantics, ensuring privacy while maintaining usability for medical professionals. The system was implemented in a prototype environment and evaluated through stress testing with up to 200 users, achieving an average CPU usage of 55% and a memory consumption of 80.2 MB. Differential cryptanalysis demonstrated a strong avalanche effect (~50%), with no vulnerabilities found via OWASP ZAP scanning. This architecture offers a promising solution for privacy-preserving, patient-controlled EHR systems, particularly in regions with limited infrastructure