Abstract:Student mental health disorders have become an increasingly important issue due to their significant impact on academic performance and psychological well-being. Machine learning-based approaches offer a promising alternative…
ative for supporting early detection; however, only a limited number of studies have conducted comprehensive evaluations of various ensemble learning algorithms by simultaneously considering predictive performance, computational efficiency, and statistical significance. This study aims to compare ten classification algorithms, namely Random Forest, Extra Trees, Gradient Boosting, Hist Gradient Boosting, AdaBoost, XGBoost, LightGBM, CatBoost, Logistic Regression, and Stacking Ensemble, using 5-fold Stratified Cross-Validation. Model performance was evaluated using Accuracy, Precision, Recall, F1-Score, Receiver Operating Characteristic–Area Under the Curve (ROC-AUC), training time, inference time, confusion matrix, feature importance, as well as One-Way Analysis of Variance (ANOVA) and post-hoc Tukey’s Honestly Significant Difference (Tukey HSD) tests. The experimental results show that CatBoost achieved the highest classification performance, with an Accuracy of 84.86%, an F1-Score of 87.19%, a Recall of 88.03%, and an ROC-AUC of 0.9220. XGBoost delivered comparable predictive performance with a substantially shorter training time (3.92 seconds), while LightGBM was the most computationally efficient algorithm, requiring an average training time of only 0.85 seconds. In contrast, the Stacking Ensemble required the longest training time (215.41 seconds) without providing a statistically meaningful performance improvement over the boosting-based models. The ANOVA results revealed significant differences in ROC-AUC among the evaluated models (p < 0.001), whereas the Tukey HSD test indicated that most boosting algorithms did not differ significantly from one another. These findings provide practical guidance for selecting classification algorithms by balancing predictive performance and computational efficiency to support early mental health screening systems for university students.
Abstract:Every company must adapt to the digital era, and a crucial strategy for achieving this is preparing for change. Employees who are ready for change tend to operate more effectively. This research aims to determine whether…
self-efficacy predicts readiness for change among digital enterprise employees. The study used a quantitative approach with a survey design. The sample comprised 106 digital enterprise employees. Data were collected using a 25-item Readiness to Change Questionnaire and a 10-item General Self-Efficacy Scale (GSES) instrument. The validity test utilized content and construct validity, ensuring the instruments accurately measure the intended constructs. The reliability test, using Cronbach's Alpha, ranged from 0.592 to 0.955, indicating varying levels of internal consistency, while the reliability of the measurement model (inner model) ranged from 0.773 to 0.961, suggesting high reliability. The results of the hypothesis testing show that (1) self-efficacy is a significant predictor of readiness for change, with a predictive relevance of 30%; (2) self-efficacy significantly influences the appropriateness dimension, with an effective contribution of 47.1%; (3) self-efficacy is a significant predictor of the management support dimension, with an effective contribution of 46%; (4) self-efficacy significantly predicts the change efficacy dimension, with an effective contribution of 47.9%; (5) however, self-efficacy is not a significant predictor of personal benefits. These findings underscore the importance of self-efficacy in enhancing employees' readiness for change within digital enterprises. Companies should focus on boosting employees' self-efficacy to improve their adaptability and effectiveness in the face of digital transformation. By recognizing and fostering the key dimensions influenced by self-efficacy, organizations can better support their workforce during periods of change. Overall, this research contributes to the understanding of psychological factors that facilitate successful change management in the digital era.
Abstract:This study aims to describe the effect of a cybergogy-based approach supported by an e-module in fostering students’ digital literacy on the topic of mixture separation. Motivated by the demands of Industry 4.0/Society 5.0…
5.0 and low literacy outcomes (e.g., PISA 2022) as well as preliminary findings at SMP Negeri 1 Bagor—where only 50% of students surpassed the Minimum Mastery Criterion (KKM) of 70 in science—the research employed a pre-experimental one-shot case study design with 32 Grade VIII-D students. Digital-literacy performance was measured through a verified posttest and analyzed descriptively and inferentially. Shapiro–Wilk testing indicated non-normality, so a Wilcoxon test was conducted against the KKM benchmark. The mean posttest score was 82.28 (min 75.00; max 91.66), with average achievement across components of 79% (high category); hypertext navigation was the strongest component (94%, very high), while content evaluation was the weakest (64%, high). The Wilcoxon test yielded Asymp. Sig (2-tailed) < 0.001, indicating a significant improvement relative to the benchmark. These findings suggest that the cybergogy-assisted e-module is effective for cultivating students’ digital literacy in mixture separation, with device-access constraints noted as a practical limitation for future implementations.
Abstract:In an uncertain economic climate, a large global retailer used AI-powered spend intelligence to move $220 million from indirect operational costs toward high-impact R&D. In a difficult recession, this decisive step boosted…
ed revenue by 11%, demonstrating the transformative impact of effective capital management. This achievement contrasts with "spend blindness," where industry studies show most financial leaders struggle to link expenditure patterns to strategic growth outcomes and resort to reactive cost-cutting. This study addresses this crucial gap. A thorough mixed-methods approach including a global survey of 400 CFOs, longitudinal case studies of ten multinational organizations, and advanced predictive modeling substantiated a new paradigm. Research shows that companies that understand AI-driven spend orchestration develop 7.3% faster than competitors. This premium comes from a 37% improvement in the Growth Efficiency Ratio (GER), a critical statistic for translating savings into innovation, and 5.8 times more strategic investment opportunities than standard financial approaches allow. The Spend Intelligence Quotient (SIQ), a groundbreaking statistic that assesses financial agility through integrated spend monitoring, predictive analytics, and rapid capital reallocation, is key to this advantage. This paper introduces the empirically based Spend Orchestration Framework and the requirements for the 2025 AI Finance Stack to obtain SIQ >80, the empirically proven threshold for sustainable competitive advantage. The message is clear: finance chiefs must go beyond oversight. Today's CFO may use predictive contracting and algorithmic governance to turn spend data into strategic leverage, ensure resilience, and capture disproportionate value in.
Abstract:The increased integration of operational technology (OT), Internet of Things (IoT), and business IT systems has allowed sophisticated attackers to circumvent isolated security features and launch cross-platform assaults.…
Current fragmented techniques, with discrete detectors monitoring Modbus, Kubernetes, MQTT, or other domain-specific protocols, cannot handle cross-system risks. These methodologies overlook 68% of multi-vector marketing that uses both physical and digital channels. This study introduces a transfer learning architecture to integrate detection capabilities by correlating threats across protocols, devices, and settings. The architecture generates a unified feature space that extracts behavioral semantics from industrial control system logs, cloud telemetry, network traffic, and device-level signals to produce protocol-agnostic threat representations. Adversarial domain adaptation and semantic graph embeddings enable cross-domain knowledge transfer with minimum retraining. Security teams may now discover kill chains like infected cloud containers preceding illegal PLC command execution every 23 minutes. Validated against real-world attack datasets from water treatment facilities (OT) and cloud infrastructure (IT), the system achieved 93.4% cross-platform attack recall, a 41.3 percentage point improvement over prior methodologies. It reduced OT data labeling by 89% and false positives by 93.5%. This paradigm shift transforms threat correlation from a reactive, domain-specific process to adaptive intelligence, boosting resilience for critical infrastructure, industrial ecosystems, and smart environments facing cyber-physical hazards. The framework's practical validation in energy, industry, and vital infrastructure shows its importance in protecting an increasingly linked world.
Abstract:In the era of globalization and increasingly intense competition, the management of Human Resources (HR) has become a crucial factor for ensuring company sustainability and growth. This study aims to explore the impact of…
f HR optimization on a company's financial health using a qualitative approach. Employing a case study methodology, the research analyzes companies that have successfully implemented effective HR strategies, including employee development, competitive compensation policies, performance management, and wellness programs. Data was collected through in-depth interviews with HR managers, executives, and employees, as well as internal document analysis and direct workplace observation. The findings indicate that effective HR practices can reduce costs, enhance productivity, and lower turnover rates, all contributing to improved financial performance. The results support Wright and McMahan's (2011) theory that effective HR management acts as an enabler for achieving competitive advantage. The study also aligns with Huselid’s (1995) research, which highlights the importance of competitive compensation policies in boosting productivity and financial health. This research underscores the significance of aligning HR strategies with financial goals and adopting best practices in HR management to improve operational efficiency and achieve sustainable financial objectives.
Abstract:This study examines the influence of Foreign Direct Investment (FDI) and Micro, Small, and Medium Enterprises (MSMEs) on economic growth and its impact on unemployment reduction in the Province of DKI Jakarta. The analysis…
is reveals a significant positive correlation between FDI and economic growth, highlighting the role of foreign capital, technology transfer, and managerial expertise in boosting regional productivity. Similarly, MSMEs contribute significantly to the Gross Regional Domestic Product (GRDP) and employment creation, supported by government policies facilitating access to finance, training, and business support. The study also finds that economic growth driven by FDI and MSMEs effectively reduces unemployment rates. Recommendations for policymakers include creating a favorable investment climate, strengthening MSME support, ensuring inclusive economic growth, and enhancing public-private collaboration. These measures aim to sustain the positive impact of FDI and MSMEs on economic development and job creation in DKI Jakarta.
Abstract:Exploring the multifaceted dynamics of customer loyalty in Islamic banking, this study investigates the roles of trust and corporate image in Eastern Indonesia's Islamic banking sector. Employing structural equation modelling…
lling (SEM) as the analytical tool, the research uncovers the intricate interplay between corporate image, trust, and customer loyalty. Results indicate that a solid corporate image significantly and positively influences customer trust. This trust is crucial in boosting customer loyalty towards Islamic banking services. Highlighting the importance of corporate image, the study reveals its role as a cornerstone in building and reinforcing customer trust, which is crucial for fostering long-term customer relationships. The research provides strategic insights for Islamic banks in Eastern Indonesia, suggesting that a focus on enhancing corporate image and trust can lead to increased customer loyalty. This contribution enriches the understanding of loyalty dynamics within the Islamic banking sector, underscoring the significance of trust and corporate image in the unique market context of Eastern Indonesia.
Abstract:Penggunaan dompet digital yang terus meningkat menghasilkan banyak ulasan pengguna yang dapat dimanfaatkan untuk mengevaluasi kualitas layanan. Penelitian ini bertujuan meningkatkan akurasi klasifikasi sentimen pengguna…
dompet digital menggunakan metode Stacking Ensemble Machine Learning yang mengombinasikan Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), dan AdaBoost dengan Logistic Regression sebagai meta-learner. Data ulasan diproses melalui tahapan text preprocessing meliputi case folding, cleaning, tokenizing, stopword removal, stemming, dan pembobotan fitur menggunakan TF-IDF. Penyeimbangan data dilakukan dengan SMOTE, sedangkan evaluasi model menggunakan 5-Fold Cross-Validation. Hasil penelitian menunjukkan bahwa model Stacking Ensemble memperoleh akurasi rata-rata 80,55%, lebih tinggi dibandingkan algoritma dasar. Evaluasi menggunakan Confusion Matrix, Classification Report, dan ROC Curve juga menunjukkan peningkatan nilai precision, recall, F1-score, dan kemampuan diskriminasi model. Hasil ini menunjukkan bahwa pendekatan Stacking Ensemble Machine Learning efektif untuk meningkatkan akurasi klasifikasi sentimen pengguna dompet digital serta mendukung evaluasi kualitas layanan berbasis opini pengguna.
The rapid growth of digital wallet usage has generated a large volume of user reviews that can be utilized to evaluate service quality. This study aims to improve the accuracy of digital wallet user sentiment classification using a Stacking Ensemble Machine Learning approach that combines Support Vector Machine (SVM), Multinomial Naïve Bayes (MNB), and AdaBoost with Logistic Regression as the meta-learner. User reviews were processed through text preprocessing stages, including case folding, text cleaning, tokenization, stopword removal, stemming, and TF-IDF feature weighting. Synthetic Minority Over-sampling Technique (SMOTE) was employed to address class imbalance, while model performance was evaluated using 5-Fold Cross-Validation. The experimental results show that the proposed Stacking Ensemble model achieved an average accuracy of 80.55%, outperforming the individual base learners. Furthermore, evaluations based on the Confusion Matrix, Classification Report, and Receiver Operating Characteristic (ROC) Curve demonstrated improvements in precision, recall, F1-score, and the model's discriminative capability. These findings indicate that the proposed Stacking Ensemble Machine Learning approach is effective in improving the accuracy of digital wallet user sentiment classification and can serve as a reliable tool for supporting service quality evaluation based on user opinions.
Abstract:This study analyzes the influence of brand experience, application ease of use, and perceived quality on customer satisfaction and its impact on customer loyalty in the PIJAR Sekolah application. The research focuses on…
users from public junior high schools, vocational high schools, and senior high schools in West Bandung Regency. A quantitative method was employed using a survey distributed to students and educators. The data were analyzed using Structural Equation Modeling (SEM). Results show that brand experience, ease of use, and perceived quality significantly influence customer satisfaction. Furthermore, customer satisfaction plays a critical role in driving customer loyalty. The study emphasizes the importance of enhancing user interaction, simplifying application navigation, and ensuring content quality to boost satisfaction and long-term usage. These findings offer insights for educational technology developers to improve digital learning platforms and foster user loyalty through an optimized experience.