Publication Search

Computers in one of the network companies at PT. Estrada uses the Fortinet operating system. The final result expected through this implementation is to comprehensively see the capabilities of the firewall on Fortinet in overcoming the problem of blocking social media applications and streaming platforms during working hours. Blocking the application in question is the ability to filter web processes such as Facebook, Instagram, YouTube, etc. In the tests carried out, web filtering was able to block applications on social media and streaming platforms, which proves that the performance of web filtering is quite good. In analyzing web filtering performance, use the office hour rule tool by carrying out the rule schedule in the Fortinet network and displaying all the information in detail. The final result obtained in the network application filtering simulation process using Fortinet is that every network sent cannot be entered (blocked) on both social media applications and streaming platforms.

This study conducts a systematic review of literature concerning the role of Management Information Systems (MIS) in managing Umrah pilgrim data across Indonesia. Employing a Systematic Literature Review (SLR) guided by the PRISMA protocol, the study examined and synthesized 24 peer-reviewed articles published between 2019 and 2026, drawn from Google Scholar, SINTA, and nationally accredited journal portals. Findings indicate that MIS adoption has yielded notable improvements in operational efficiency, data reliability, service transparency, and the overall quality of managerial decision-making within Umrah travel organizations. Web-based MIS remains the predominant technological approach, offering integrated modules for pilgrim registration, document handling, financial tracking, and departure scheduling. At the national level, government-initiated platforms such as SISKOHAT and SISKOPATUH have demonstrated tangible contributions to the administration of Hajj and Umrah services. Nevertheless, persistent obstacles continue to hinder full-scale adoption, including inadequate digital infrastructure in certain regions, inconsistent internet connectivity, and gaps in human resource competencies for operating digital systems. The study argues that embracing MIS is no longer optional for Umrah travel operators; rather, it constitutes a strategic necessity. Future research is encouraged to investigate long-term implementation outcomes, cross-system comparisons, and data security considerations within the broader digital landscape of pilgrimage service management.

The problem of stunting is still a serious issue in health development in Indonesia because it has an impact on the quality of human resources. This study aims to analyze the efforts of the Pagomogo Village Government in handling stunting. The research uses a descriptive qualitative approach with data collection techniques through observation, interviews, and documentation. Informants were determined using purposive sampling consisting of village governments, health workers, cadres, and the community. The results of the study show that the village government has implemented various programs, such as Supplementary Feeding (PMT), strengthening Human Development Cadres (KPM), improving services through community institutions, and sanitation development. However, the implementation of the program has not been optimal because it is still constrained by economic factors, low public awareness, limited counseling, and access to clean water. This study concludes that the main problem does not lie in the availability of programs, but in the implementation and sustainability aspects. Therefore, it is necessary to strengthen community empowerment, improve education, and evaluate results-based programs.

Human Trafficking (TPPO) has undergone a significant transformation in its modus operandi alongside the massive use of information technology, giving rise to the phenomenon of cyber-recruitment within the online scam industry. This study aims to analyze the juridical construction of the criminal elements in the cyber-recruitment modus operandi based on Law Number 21 of 2007, and to evaluate the potential disharmony of norms between the TPPO regulation and the Electronic Information and Transactions Law (UU ITE) regarding the regulation of digital evidence. The research method employed is normative legal research with a statutory approach and a conceptual approach. The results indicate that, dogmatically, the elements of TPPO—comprising the process of virtual recruitment, the means of fraudulent job promises, and the purpose of digital forced labor exploitation—under Law No. 21 of 2007 remain relevant for prosecuting cyber-recruitment perpetrators, although it demands a broader legal interpretation of cyberspace realities. However, legal certainty issues were found due to the lack of synchronicity in the regulation of digital evidence, where differences in procedures and qualifications exist between electronic evidence in the TPPO Law and the evidentiary standards in the UU ITE, which are volatile in nature. The implications of this research conclude the need for regulatory synchronization through the establishment of technical guidelines for handling TPPO-specific electronic evidence to provide a solid legal foundation for law enforcement agencies. This step is crucial to overcome cross-border jurisdictional obstacles and to ensure substantive justice and comprehensive protection of victims' rights in the digital era.

This study examines customer churn prediction in subscription-based telecommunications from a digital marketing perspective using machine learning. The analysis utilizes a secondary dataset of 7,043 customer records that simulate behavioral, contractual, and financial attributes commonly found in telecom services. Three classification algorithms Logistic Regression, Random Forest, and Gradient Boosting are applied to model churn behavior. Data preprocessing includes handling missing values, encoding categorical variables, and splitting data into training and testing sets. Model performance is evaluated using accuracy, recall, and ROC-AUC, with emphasis on recall due to its importance in identifying at-risk customers. The results show that Gradient Boosting achieves the highest overall performance with an ROC-AUC of 0.84, while Logistic Regression provides relatively higher recall. Key drivers of churn include short-term contracts, higher monthly charges, and lower service engagement. However, recall remains moderate, indicating limitations in capturing complex behavioral factors. These findings suggest the need to combine predictive models with behavioral insights and highlight the importance of early customer engagement and long-term retention strategies.

The proliferation of online gambling promotional comments on Indonesian social media has become a serious issue requiring fast and accurate automated handling. This study aims to implement a Hybrid Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) method to classify online gambling comments and compare its performance with standalone RNN and LSTM models. The research utilized a dataset of 10,230 comments subjected to comprehensive preprocessing stages, including the normalization of non-standard language using a slang dictionary. Testing was conducted across three data-splitting scenarios: 90:10, 80:20, and 70:30. Experimental results demonstrate that the standalone LSTM model achieved the highest average accuracy of 97.45%. However, the Hybrid RNN–LSTM model showed significant superiority in terms of performance stability, yielding the lowest standard deviation (0.0027) and the smallest Coefficient of Variation (0.28%) across all scenarios. These findings indicate that while the LSTM architecture is highly effective at capturing short-text context, the Hybrid approach provides better robustness against fluctuations in data proportions, making it highly relevant for implementation as an automated detection system on social media.

This study aims to design and develop a waste complaint information system at the Environmental Agency of West Sumba Regency to improve the effectiveness of public services. The current problem lies in the manual complaint process, which leads to delays in handling reports, poor data documentation, and limited service transparency. This research employs a qualitative descriptive approach with data collection techniques including observation, interviews, and documentation studies. The system development adopts the Waterfall method, which consists of requirement analysis, system design, implementation, testing, and maintenance stages. The system is modeled using Unified Modeling Language (UML), including use case diagrams, activity diagrams, and sequence diagrams to provide a structured representation of the system. This approach is considered effective as it ensures a systematic and well-organized development process. The results indicate that the developed system facilitates the public in submitting complaints online and assists the agency in managing complaint data in an integrated manner. Furthermore, the system enhances response time, transparency, and service efficiency. Therefore, this waste complaint information system can serve as a technological solution to improve the quality of public services.

For criminal justice systems, the growing number of young people involved in drug-related crimes is a serious problem, especially when it comes to striking a balance between law enforcement and child protection and rehabilitation. By contrasting viewpoints from Islamic law and Indonesian positive law, this study investigates the use of restorative justice in the processing of adolescent drug cases in Tanjung Jabung Barat Regency, Jambi. The study used a qualitative socio-legal methodology that integrates normative legal analysis with empirical field data gathered via observations, interviews, and document analysis involving law enforcement personnel, rehabilitation facilities, families, and community people. The results show that diversionary measures required by Law No. 11 of 2012 regulating the Juvenile Criminal Justice System are the main means by which restorative justice is applied in juvenile drug cases. In order to guarantee that children are not subjected to punitive detention but rather have options for recovery and social reintegration, these systems prioritize mediation, rehabilitation, and community involvement. From the standpoint of Islamic law, restorative justice is consistent with fundamental tenets like tawbah (repentance), islah (reconciliation), and the protection of human welfare, all of which place an emphasis on moral reform and the preservation of children's dignity. These ideas support the adoption of restorative measures in the resolution of adolescent drug offenses in Tanjung Jabung Barat, a sociocultural setting where Malay-Islamic beliefs have a significant impact on community life. The report does, however, also point out a number of difficulties, such as the lack of rehabilitation facilities, the societal stigma associated with juvenile offenders, and the inconsistent use of diversion by law enforcement. The study comes to the conclusion that a framework for handling juvenile drug cases that prioritizes the rehabilitation and future well-being of children is both culturally sensitive and legally sound when restorative justice ideas are integrated with Islamic legal values and Indonesian statutory law.

Terrorism is a serious threat to the security and unity of the Indonesian nation. Events such as the suicide bombing at the Medan Police Headquarters in 2019 show that acts of terror are increasingly complex and require swift and appropriate handling. For this reason, the government passed Law Number 5 of 2018 concerning the Eradication of Criminal Acts of Terrorism as a legal basis that strengthens the authority of the apparatus, including the Gegana Detachment of the Indonesian National Police Mobile Brigade Corps (Brimob), in carrying out counter-terrorism operations. This study aims to determine and analyze how the implementation of Law No. 5 of 2018 is carried out by the Gegana Detachment in the North Sumatra Regional Police area, identify obstacles faced in operations, and formulate strategies to increase the effectiveness of the implementation of the law. The results of the study show that the implementation of this law has been implemented through preventive, preemptive, and repressive approaches, such as sterilization of places of worship, social activities "Love Sunday", security patrols, and anti-terror training simulations. However, implementation in the field still faces various obstacles, including limited modern equipment, lack of cross-agency coordination, and low public participation. Therefore, personnel capacity building, infrastructure modernization, and strengthening inter-agency synergy are needed to achieve more effective counterterrorism efforts in North Sumatra.

Terrorism is a serious threat to the security and unity of the Indonesian nation. Events such as the suicide bombing at the Medan Police Headquarters in 2019 show that acts of terror are increasingly complex and require swift and appropriate handling. For this reason, the government passed Law Number 5 of 2018 concerning the Eradication of Criminal Acts of Terrorism as a legal basis that strengthens the authority of the apparatus, including the Gegana Detachment of the Indonesian National Police Mobile Brigade Corps (Brimob), in carrying out counter-terrorism operations. This study aims to determine and analyze how the implementation of Law No. 5 of 2018 is carried out by the Gegana Detachment in the North Sumatra Regional Police area, identify obstacles faced in operations, and formulate strategies to increase the effectiveness of the implementation of the law. The results of the study show that the implementation of this law has been implemented through preventive, preemptive, and repressive approaches, such as sterilization of places of worship, social activities "Love Sunday", security patrols, and anti-terror training simulations. However, implementation in the field still faces various obstacles, including limited modern equipment, lack of cross-agency coordination, and low public participation. Therefore, personnel capacity building, infrastructure modernization, and strengthening inter-agency synergy are needed to achieve more effective counterterrorism efforts in North Sumatra.

This research benchmarks multiple machine learning (ML) algorithms for large-scale loan default prediction using a real-world dataset of 255,000 borrower records, where default cases represent only ~9–12% of total observations. The study addresses the persistent gap in comparative analyses of ML models that balance predictive accuracy, interpretability, and computational efficiency for credit risk assessment. Six algorithmic families were evaluated Logistic Regression, Random Forest, XGBoost, LightGBM, CatBoost, Artificial Neural Networks (ANN), and Stacked Ensemble—using standardized preprocessing, hybrid imbalance handling (SMOTE, class weighting, under-sampling), and comprehensive evaluation metrics (AUC, F1, Recall, Precision, PR-AUC, and Brier Score). Empirical results show Logistic Regression achieved the highest AUC of 0.732, outperforming nonlinear models under the baseline configuration, while LightGBM attained perfect recall (1.0) but low precision (0.116), indicating over-prediction of defaults. Gradient boosting models demonstrated robust calibration (Brier ≈ 0.114–0.116) and the best computational efficiency, with LightGBM showing the fastest training and lowest memory use. CatBoost exhibited strong recall but the slowest computation, and ANN underperformed on tabular data (AUC ≈ 0.56). The Stacked Ensemble delivered balanced results with AUC = 0.664 and improved overall stability. These findings confirm that boosting-based models, particularly LightGBM and CatBoost, offer superior scalability and calibration, whereas Logistic Regression remains a valuable interpretable baseline. The study concludes that effective default prediction requires integrating rebalancing, calibration, and threshold optimization to enhance recall and operational deployment reliability in large-scale credit ecosystems.

The rupiah plays a vital role as a symbol of national identity and sovereignty, but awareness among rural communities about its function and importance is often limited. In Kutalimbaru Village, the main challenges identified are low monetary literacy, which results in physical damage to money and a lack of awareness about counterfeit money. Through the Real Work Lecture (KKN) program, community service efforts were carried out with the aim of internalizing the values of “Love, Pride, Understanding (CBP) of the Rupiah.” The approach used was community-based education through interactive workshops and practical demonstrations on money care techniques and an introduction to the security features of the Rupiah. Findings in the field show a transformation in the community's attitude; from being indifferent to being more careful in handling paper money and better understanding the role of the Rupiah in economic stability. This program has succeeded in increasing the financial literacy of citizens while strengthening the spirit of nationalism through appreciation of the national currency. Keywords: community empowerment, micro businesses, tempeh products, entrepreneurship, Sialaman Village.

Stunting is a complex public health problem that requires a multisectoral approach in its management. This community service aims to increase the capacity of village officials and Village Consultative Body (BPD) in handling stunting through the strategic role of management higher education institutions. The method used is a participatory approach involving 18 participants consisting of village officials and BPD members. The activities were carried out through stages of needs analysis, stunting program management training, action plan development assistance, and monitoring evaluation. The results showed a significant increase in participants' understanding of stunting program management (from 45% to 85%), the formation of a stunting management working team at the village level, and the preparation of a comprehensive stunting management action plan. The social change that has been realized is increased cross-sectoral coordination in handling stunting and the formation of a data-based monitoring system at the village level. Management higher education institutions play a strategic role in building the managerial capacity of village officials to manage stunting programs effectively and sustainably.

This study examines the influence of memorable tourism experiences and operational risk management in tourist train transportation on positive Word of Mouth (WOM), with tourist satisfaction serving as a mediating variable. A quantitative approach was employed, and data were processed using SEM-PLS 4. The research sample consisted of 247 respondents who had used tourist train services within the past year. The results reveal that both effective risk management practices and memorable tourism experiences perceived by tourists significantly impact tourist satisfaction. Additionally, tourist satisfaction plays a crucial mediating role in generating positive WOM. The study highlights that memorable tourism experiences, including aspects such as comfort, scenic views, and the quality of service, significantly enhance tourist satisfaction. Furthermore, operational risk management, which includes ensuring passenger safety, maintaining service reliability, and handling emergencies effectively, is essential for cultivating satisfaction and positive WOM. The findings suggest that businesses in the tourism industry, particularly those operating tourist trains, should prioritize both risk management and creating memorable experiences to foster customer loyalty and enhance WOM. This study contributes to understanding the dynamic relationship between risk management, customer satisfaction, and WOM in the tourism sector, providing valuable insights for improving service strategies in tourist train transportation.

Consumers are divided into three categories: initial consumers, middle consumers, and end consumers. These three types of consumers certainly have the right to protection, but end consumers as users need to receive more attention to protection, especially in the buying and selling process. This study uses a sociolegal approach with a purposive sampling method to examine the selling process. In addition, this study also examines how protection for end consumers is implemented in LPG buying and selling activities in Balikpapan Tengah District. Thus, this study aims to contribute to the understanding of protection efforts and the impact of not implementing protection properly in Balikpapan Tengah District, a densely populated area. This study is expected to be a reference for the development of consumer protection efforts in the buying and selling of subsidized LPG, as well as providing insight into the consequences that can be received by end consumers and their handling in the future.

Gender-based domestic violence (KDRT) remains a critical issue in Indonesia, particularly in urban areas like North Jakarta. This study examines the governance of services for KDRT victims from a gender perspective in 2025, employing a qualitative case study approach. Data were gathered through in-depth interviews with 20 victims and service providers at community health centers (Puskesmas), the Women's Empowerment and Child Protection Agency (DP3A), and NGOs. Findings reveal fragmented governance, characterized by weak inter-agency coordination, low accessibility for low-income victims, and insufficient integration of gender perspectives in handling procedures. Key barriers include bureaucratic hurdles and inadequate training for staff on toxic masculinity issues. The study recommends an integrated governance model based on gender-responsive governance, including a one-stop digital platform and enhanced multi-stakeholder collaboration. Policy implications support the achievement of SDGs 5 and 16 at the local level. This study also highlights the importance of increasing public awareness and education regarding gender-based domestic violence to create a safer and more inclusive environment for victims.

Slums are an urban issue that arises due to rapid population growth and the limited capacity of local governments to provide adequate housing and basic infrastructure. This leads to areas with low environmental quality, limited access, poor drainage, and high socio-economic vulnerability. A similar phenomenon occurs in Jambi City, which requires a sustainable handling strategy. This study aims to analyze the strategies implemented by the Department of Public Housing and Settlement Areas of Jambi City in addressing slums and assess their contribution to environmental quality. A descriptive qualitative approach was used to understand the policies, program implementation mechanisms, and institutional challenges. Data was collected through interviews with government officials, field observations, and analysis of planning documents. The results indicate that the strategy focuses on improving basic infrastructure, such as road construction, drainage rehabilitation, and the provision of settlement facilities. This program enhances environmental quality and accessibility but faces challenges such as budget limitations, suboptimal inter-agency coordination, and the socio-economic conditions of the community. Addressing slums requires a more comprehensive approach, including collaborative governance, increased community participation, and adaptive policies to ensure sustainable improvements.

Heart disease is the leading cause of death in Indonesia and globally, necessitating an early screening system that is both accurate and clinically trustworthy. Although XGBoost demonstrates high predictive performance, its black-box nature undermines clinical trust, while low recall risks missed diagnosis an unacceptable consequence in population screening, especially in middle-income countries with limited healthcare resources. This study aims to develop a sensitive, transparent, and implementation-ready heart disease screening framework through the integration of SHAP-based Explainable AI. The CDC's Indicators of Heart Disease dataset (319,795 samples) was processed according to WHO/CDC standards, followed by class imbalance handling, hyperparameter optimization using RandomizedSearchCV, evaluation based on metrics sensitive to minority classes (AUC, recall, F1-score, AUC-PR), and threshold tuning to maximize recall. The baseline model showed a very low recall of 12.18%. After optimization and threshold tuning at 0.10, the model achieved recall >96% (96.79%) with a G-mean of 0.7477, supported by SHAP interpretation stability and the ability to capture non-linear interactions between advanced age (AgeCategory_WHO) and poor general health (GenHealth). SHAP analysis confirmed the alignment of dominant features with medical evidence, and its visualizations provide transparent explanations for healthcare professionals indicating its potential implementation as an interpretable clinical decision support system.

This community service activity aims to improve the First Aid Awareness of students at SMAN 5 Tegal through health education and first aid simulation for accident management. The background of this program is based on the high potential for mild to moderate emergency incidents in the school environment, such as fainting, open wounds, nosebleeds, choking, and seizures, as well as the limited knowledge and practical skills of students in providing appropriate initial assistance. The implementation method consisted of three stages: preparation, delivery of health education using presentations and demonstrations, and hands-on simulation, followed by evaluation through knowledge assessment and skills observation. The participants were 54 students representing three grade levels. The expected outcomes of this activity include an improvement in students’ conceptual understanding and practical ability to perform first aid quickly, correctly, and safely before professional medical help arrives. In addition, this program is expected to foster emergency responsiveness, increase students’ confidence in handling accident situations at school, and contribute to the development of a safer and more prepared school environment. The outputs of this activity include increased knowledge and skill scores, documented implementation, and publication of a community service article in a SINTA-indexed journal.

This research develops a machine learning model to classify customer loyalty using the Random Forest algorithm. Customer churn is a critical issue that reduces revenue and increases acquisition costs. A dataset of 50,000 customers from global e-commerce and subscription platforms was processed through data cleaning, imputation, outlier handling, and class balancing with SMOTE. The Random Forest model was built as a baseline and optimized with hyperparameter tuning. Evaluation using accuracy, precision, recall, and F1-score shows that the optimized model achieved 90.81% accuracy and 83.87% F1-score, outperforming previous Naïve Bayes approaches. Feature importance analysis highlights customer service interactions, lifetime value, and demographic factors as key predictors of churn. These findings demonstrate Random Forest’s effectiveness in churn prediction and provide practical insights for customer retention strategies