Jurnal Informatika dan Rekayasa Perangkat Lunak

Decision Support System Based on RECA and COPRAS Methods in Performance Evaluation of Non-Permanent Employees

Ayuni Asistyasari — 2025-09-15

The evaluation of the performance of non-permanent employees is a significant challenge for organizations due to the high turnover rate and the limited tenure of these employees. The manual evaluation processes often lead to biases, inconsistencies, and a lack of accuracy in supporting decision-making. This research aims to develop a decision support system based on the RECA and COPRAS methods to produce a more objective, transparent, and systematic evaluation. RECA is used to determine the criteria weights proportionally based on each contribution, while COPRAS functions to assess and provide a final ranking of employee performance by considering both benefit and cost-type criteria. The research results show that this system is capable of sorting non-permanent employees fairly with ranking results of E-AS-05 with a score of 100%, E-AS-03 with a score of 97.32%, E-AS-01 with a score of 94.03%, E-AS-02 with a score of 88.34%, and E-AS-04 with a score of 82.19%. The integration of the RECA and COPRAS methods not only enhances the effectiveness of performance evaluation but also provides a tangible contribution to supporting more efficient and sustainable human resource management.

Web-Based Tracer Study Information System Development Using Rapid Application Development for Alumni Data Management in FMIPA UNSRAT

Timothy Salomo Van Dijken Boediman — 2025-09-15

Tracer studies are essential tools for evaluating the relevance and quality of higher education curricula, as they facilitate the tracking of alumni career outcomes. However, the conventional utilization of Google Forms for data collection in the Information Systems Study Program at FMIPA UNSRAT has led to fragmented and inefficient alumni data management. The objective of this research is to develop a web-based tracer study information system to enhance the efficiency and accuracy of alumni data management. The system's development employed the Rapid Application Development (RAD) method, which prioritizes iterative prototyping and active stakeholder involvement. The research process entailed a multifaceted approach, encompassing a needs analysis, system design, implementation, and black-box testing to ensure system reliability. The resulting web-based system enables alumni to complete dynamic questionnaires according to their employment status, while administrators can efficiently manage and visualize alumni data through interactive dashboards. The system's structured data collection and visualization features support program evaluation and accreditation processes. Preliminary testing results indicate that the system functions as intended and significantly enhances the management and utilization of alumni data. The present study demonstrates that the integration of RAD and web-based technology provides a practical solution for tracer study implementation in higher education institutions.

Soft Voting Based Optimized Ensemble for Migraine Type Classification

Titik Misriati — 2025-09-15

The accurate classification of migraine subtypes is a complex challenge in neurology, hindered by symptomatic similarities between types. This complexity necessitates advanced computational tools to support diagnostic precision. This study aims to develop and evaluate an optimized soft voting ensemble classifier to automate this multi-class classification task effectively. The methodology involved training eight base models—including Neural Network, Random Forest, and Gradient Boosting—on a publicly available migraine dataset, with an 80-20 train-test split. The top three performers were integrated into a soft voting ensemble, which aggregates their predicted probabilities to enhance decision robustness. Model performance was rigorously assessed using accuracy, precision, recall, F1-score, and AUC-ROC metrics. The results demonstrated that the proposed ensemble achieved superior performance, with an accuracy of 91.67% and an F1-score of 91.50%, outperforming all constituent models. Furthermore, the ensemble attained near-perfect AUC-ROC values across multiple classes, confirming its strong discriminatory capability. The study concludes that the soft voting ensemble is a highly effective and reliable approach for migraine subtype classification, offering significant potential as a decision-support tool in clinical environments. Future work will focus on hyperparameter optimization, explainability, and validation with larger multi-centric datasets to facilitate clinical adoption.