Publication Search

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.

This study examines the implementation of Integrated Marketing Communication (IMC) at NailedShape, a Bali-based nail art micro-enterprise, as a strategy to foster customer loyalty. NailedShape operates under a home-service and home studio model, primarily using Instagram for promotion and customer engagement. The study utilizes a descriptive qualitative method, collecting data through interviews and observations with the owner, customers, and micro-influencers. The research findings show that NailedShape successfully employs IMC techniques, such as visual content, customer testimonials, and collaborations with digital influencers, to capture attention and create strong emotional connections with customers. This integrated approach helps in building a positive brand image and maintaining customer engagement. However, the study also highlights challenges, such as limited resources and frequent changes to social media algorithms, which hinder consistent communication and marketing efforts. Despite these obstacles, the study concludes that a well-executed IMC strategy remains effective in enhancing customer loyalty, reinforcing the importance of an integrated communication approach for small and medium enterprises (SMEs) in the beauty industry. By utilizing digital platforms effectively, NailedShape can compete in a highly dynamic market. The findings suggest that beauty-based MSMEs can benefit greatly from IMC in the digital era, as it not only enhances brand perception but also helps in building lasting customer relationships.

This study aims to analyze the role of marketplace in encouraging digital internationalization and product development at PT Bungas Food Nusantara. The research uses a qualitative approach with a case study method. Data was obtained through in-depth interviews with company management, observation of activities on the marketplace platform, and supporting documentation. The results of the study show that marketplaces function not only as digital distribution channels, but also as strategic infrastructure that allows companies to reach international markets without conventional export mechanisms. Internationalization occurs gradually through increased demand from overseas consumers facilitated by the platform's algorithmic system and global visibility. In addition, the marketplace's reviews, ratings, and analytics features are used as the basis for product development, including packaging adjustments, variant innovation, and data-driven promotional strategies. These findings show that marketplaces play a role as a catalyst for internationalization as well as a driver of product innovation in the context of the digital economy.

The development of digital culture has significantly changed the communication, relationships, and spirituality of the younger generation, requiring the Church to reconsider its catechetical methods in the context of social media. This article aims to analyze digital catechesis as a space where faith can develop for the younger generation, by examining the theological foundations, the dynamics of digital culture, and the challenges and models for its development. This study adopts a literature review method by conducting a systematic review of Church Magisterial documents, theological works, and academic research related to the religiosity of the younger generation in the digital environment. The research findings indicate that social media can become a place of faith encounter if catechesis focuses not only on the delivery of religious content but also offers a relational experience that is dialogical, participatory, and community-oriented. However, there are serious challenges such as the risk of superficiality, spiritual consumption, the dominance of algorithms, the commodification of religious content, and the issue of doctrinal authority in the digital space. Therefore, the development of digital catechesis must be based on Christocentrism, fidelity to Church teaching, and a combination of online guidance and concrete sacramental life. With an approach that takes context and reflection into account, digital catechesis has the potential to be a significant and transformative tool of evangelization for young people in the evolving culture of social media.

This study aims to analyze how the TikTok and Instagram Reels algorithms play a role in the distribution of multimedia content and their implications for content visibility, user engagement, and digital marketing practices. The research method used is a qualitative approach through a Systematic Literature Review by analyzing articles from accredited national journals and reputable international journals published in the period 2020-2025. The literature search process was carried out systematically through openly accessible scientific databases, then selected using inclusion and exclusion criteria to ensure the relevance and quality of the sources. The research findings show that the TikTok and Instagram Reels algorithms both rely on analysis of user behavior, initial engagement levels, and the characteristics of short-form audiovisual content in determining content distribution. TikTok emphasizes an interest-based recommendation system that allows content from new creators to gain broad reach, while Instagram Reels combines algorithmic recommendations with established social networks. The implications of this study emphasize that understanding the mechanics of algorithms is a strategic factor for content creators, business actors, and digital marketing practitioners in designing effective, adaptive, and sustainable multimedia content distribution strategies.

Social media has become integral to the daily lives of Generation Z (Gen Z) in Indonesia, with intensive daily usage contributing to significant mental health concerns. This narrative review synthesizes evidence from the literature published between 2021 and 2026 to examine the primary mechanisms social comparison and fear of missing out (FOMO) underlying the negative effects of social media on mental health, including anxiety, depression, low self-esteem, sleep disturbances, and social isolation. Drawing from 15 key open-access articles (including 7 Indonesia-specific studies and 8 global comparisons), social comparison through curated content on platforms such as Instagram and Facebook was consistently associated with diminished self-satisfaction and heightened dissatisfaction. FOMO, particularly amplified by fast-scrolling algorithms on TikTok, promoted compulsive behaviors such as doomscrolling and exacerbated emotional distress. Digital wellness strategies, including digital detox, mindful usage, and media literacy, showed promising potential for mitigation, although long-term effectiveness remains limited in the Indonesian context. Notable research gaps include the scarcity of longitudinal studies, culturally tailored interventions, and data from rural or non-urban populations. This review recommends integrating digital literacy education into school curricula and developing community-based mental health programs to address risks in the 2025–2026 digital era. The findings offer insights for prevention and intervention strategies targeting Gen Z mental health in Indonesia.

This study aims to provide a comprehensive analysis of Predictive Policing and its implications for law enforcement transformation in Indonesia, based on an extensive review of its global applications, benefits, and challenges. The study uses qualitative literature and international case study review methods to assess the impact and complexity of implementing digital technologies such as artificial intelligence (AI), machine learning, and big data analytics within a Predictive Policing framework. The results of this review highlight that while Predictive Policing offers significant potential for proactive crime prevention and increased operational efficiency, its implementation is consistently fraught with critical legal, ethical, and technical challenges, including regulatory gaps, risks of algorithmic bias, and data privacy concerns, which are particularly relevant to Indonesia. The findings underscore that public trust and police legitimacy in the context of adopting such technologies are strongly influenced by transparency, strong accountability mechanisms, and community involvement in shaping their use. This study contributes to the growing discourse on digital policing in developing countries and culminates in practical policy recommendations designed to guide the Indonesian police towards the development and implementation of Predictive Policing models that are effective, efficient, and fundamentally respectful of legal and human rights principles.

This study presents a comprehensive comparative analysis of four traditional machine learning algorithms Decision Tree, Random Forest, K-Nearest Neighbors, and Support Vector Machine for Android malware detection using the preprocessed TUANDROMD dataset comprising 4,465 instances and 241 features representing both static and dynamic application characteristics. Motivated by the limitations of conventional signature-based and hybrid detection methods, especially in managing imbalanced datasets and detecting emerging malware variants, the study employed SMOTE to ensure balanced training data and fair model evaluation. The dataset was divided into 80% training and 20% testing subsets, and models were assessed using key performance metrics including accuracy, precision, recall, F1-score, and ROC AUC. The findings revealed that the proposed Random Forest model outperformed the other classifiers, achieving an accuracy of 0.993, precision of 0.992, recall of 1.000, F1-score of 0.996, and a near-perfect ROC AUC of 0.9998 surpassing state-of-the-art approaches. These results affirm the superior predictive capability, consistency, and robustness of the Random Forest algorithm in Android malware detection. The study concludes that base models, when integrated with class-balancing techniques, provide reliable and efficient malware detection across imbalanced datasets. For future research, the study recommends exploring advanced hybrid or ensemble frameworks that integrate Random Forest with deep learning architectures or other meta-heuristic optimization techniques to further enhance detection accuracy, adaptability, and resilience against rapidly evolving Android malware threats.

Artificial Intelligence (AI) is increasingly recognized as a transformative enabler of early disease detection, with the potential to improve diagnostic accuracy, support predictive risk stratification, and advance preventive healthcare. Despite rapid methodological progress, many existing reviews remain performance-centric, offering limited insight into generalizability, ethical governance, and real-world implementation constraints. This paper presents a narrative and integrative review with an adoption-focused, translational perspective, synthesizing recent developments in AI-driven early disease detection across oncology, cardiology, neurology, and infectious disease surveillance. Drawing on peer-reviewed literature published primarily between 2016 and 2025, the review examines reported performance gains alongside persistent limitations related to data heterogeneity, population bias, explainability, and regulatory fragmentation. Through cross-sectional synthesis, we identify three recurring gaps in prior reviews: (i) overgeneralization of AI’s diagnostic superiority, (ii) insufficient consideration of ethical and legal accountability, and (iii) a lack of actionable guidance for scalable clinical implementation. Integrating technical, ethical, and policy dimensions into a unified conceptual framework, this review demonstrates that while AI systems can consistently enhance diagnostic accuracy and early risk stratification in well-defined tasks, sustained clinical adoption depends on aligning technical performance with governance readiness, interpretability, and workflow integration. The analysis further highlights how implementation mechanisms—such as explainable AI, continuous post-deployment monitoring, and clinician-centered deployment strategies—mediate the translation of algorithmic innovation into real-world healthcare impact. Overall, this review provides a critical reference for researchers, clinicians, and policymakers seeking to translate AI innovation into safe, equitable, and trustworthy clinical practice.

Indramayu mango is a seasonal fruit that is highly favored due to its delicious taste and high nutritional content. However, high mango production is often not supported by adequate post-harvest facilities, particularly in terms of fruit ripeness classification. Currently, mango ripeness classification is still performed manually, which tends to be subjective and inconsistent. To address this issue, this study proposes a ripeness detection system for Indramayu mangoes by integrating the TGS2602 gas sensor and the YOLOv11 algorithm based on image processing. The TGS2602 sensor is used to detect ethylene gas emitted by ripe mangoes, while YOLOv11 is employed for visual image analysis of the fruit. This study aims to evaluate the system’s performance in classifying ripe and unripe mangoes, as well as analyze the integration between the gas sensor and the object detection model. The test results show that the TGS2602 sensor can detect increased ethylene gas concentration in ripe mangoes, while YOLOv11 demonstrates high accuracy in detecting mangoes based on visual images, with precision and recall close to 1.0. The system was also tested under various lighting conditions, including dark environments, and still performed well, although with a slight decrease in accuracy under low-light conditions.

The rapid growth of e-commerce in Indonesia, particularly the Shopee platform, has generated a large volume of user reviews on the Google Play Store, which can be analyzed to understand consumer sentiment. This study aims to compare the performance of the Support Vector Machine (SVM) and Random Forest (RF) algorithms in binary sentiment classification (positive and negative) on Shopee reviews, as well as to statistically test the significance of their differences using One-Way ANOVA. A total of 400,498 reviews were collected via web scraping, preprocessed through text normalization, tokenization, and Indonesian language stemming, and then feature-extracted using TF-IDF and Count Vectorizer. Evaluation results show that SVM achieved an accuracy of 91.77%, precision of 91.49%, recall of 91.77%, and F1-Score of 91.56%, while RF achieved an accuracy of 90.07%, precision of 91.68%, recall of 90.07%, and F1-Score of 90.55%. ANOVA confirmed that the performance difference between the two algorithms is statistically significant (p-value = 0.0007) with a large effect size (η² = 0.1815). Therefore, SVM is recommended as a more optimal and consistent algorithm for automated sentiment analysis of Indonesian e-commerce reviews, while also providing a replicable methodological framework for similar future research.

The spread of hoax news in digital media is a serious problem because it can affect public opinion and social stability. This study aims to classify hoax news using the Support Vector Machine (SVM) algorithm. The dataset used is a hoax clarification dataset from the Ministry of Communication and Digital (Komdigi) of the Republic of Indonesia, totaling 1,872 data. The research process includes data collection, text pre-processing, feature extraction using TF-IDF, and classification using the SVM algorithm. Implementation was carried out using Google Colaboratory (Google Colab). Test results show that the SVM algorithm is able to provide good performance in classifying hoax news based on its topic with satisfactory accuracy, precision, recall, and F1-score values.

Software Defined Network is a popular computer network concept today because of the ease of managing network traffic with the control plane. Massive internet usage makes web server services on SDN networks overloaded. There are many load balancing concepts to overcome this problem, one of which is implementing the K-NN algorithm. This study aims to maximize the performance of the K-NN algorithm on SDN networks by optimizing the K value using Grid Search Cross Validation, and adding server status selection logic based on the smallest disk if the server status calculated by K-NN has the same. All implementations of the load balancing concept in this study were created virtually using Open vSwitch and virtualbox. Testing was carried out using CPU, MEMORY, and DISK parameters sent by the server with the help of the psutils component. JMeter software was used for testing by sending data using the POST method. The data type is text/plain with a data size of 1MB, testing was carried out in stages with threads 100, 200, 300, 400. The test results showed that the performance of the K-NN algorithm was running optimally. There was no significant difference in the distribution of the load to the server, this made the optimization and addition of logic successful.

Since the announcement of the policy plan for a name transfer system in the sale of used mobile phones, the issue has attracted widespread public attention and discussion. People have expressed their opinions on social media platforms, particularly TikTok. This study aims to classify the sentiment of TikTok users using Naive Bayes and Support Vector Machine (SVM) algorithms. The data were collected through a comment scraping technique on related content.The research stages include text preprocessing, sentiment labeling into positive, negative, and neutral categories, and feature extraction using TF-IDF. The classification process employs Naive Bayes and Support Vector Machine algorithms, which are then evaluated based on accuracy, precision, recall, and F1-score. The results of this study indicate that both methods are capable of classifying sentiment effectively. However, the Support Vector Machine method is superior to the Naive Bayes method with an accuracy rate of 99.57% compared to 94.30%. This study is expected to help the government understand public responses to the planned policy of the used mobile phone name transfer system.

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

This study presents ReflectAI, a web-based system designed to automate the creation of teaching materials tailored to students' learning styles using behavior data from a Learning Management System (LMS). Student digital activity data—such as logins, material access, forum participation, assignment submission, and quiz results—are extracted and processed using a Hierarchical Clustering algorithm to categorize students into three learning styles: visual, auditory, and kinesthetic. Based on the clustering results, the system automatically generates personalized learning modules using generative AI (ChatGPT API), aligned with each student's learning preferences. Employing a data-driven system development approach, the system was tested with data from 230 students in a mathematics course. The results show diverse learning style distributions and relevant, tailored content generation. ReflectAI is designed to reduce teachers’ administrative workload and enhance personalized and adaptive learning. This system contributes to educational transformation through deep, data-driven technology integration.

This study evaluates public sentiment toward Constitutional Court Decision No. 90/PUU-XXI/2023 regarding the age limit for presidential and vice-presidential candidates, a controversial issue closely related to Indonesia’s democratic dynamics. Understanding public opinion on Twitter, as a major platform for political expression, is essential for informing electoral policy formulation. Data were collected using Tweet Harvest through Google Colab and analyzed using the Naïve Bayes algorithm as the primary sentiment classification method, with RapidMiner employed to support and streamline the analytical process. The analysis process included data cleaning, text normalization, stopword removal, manual labeling of 80 tweets as training data, and automatic sentiment classification to identify positive and negative sentiments. From a total of 151 analyzed tweets, 84 (55.63%) were classified as negative and 67 (44.37%) as positive, with the model achieving an accuracy of 66.67%. These findings suggest a tendency toward public opposition to the decision, reflecting dissatisfaction among Twitter users. The study demonstrates that Naïve Bayes is reasonably effective for sentiment classification with limited datasets and provides insights for policymakers in understanding public responses to election-related regulations.

A suitable and targeted marketing plan is required because of the intense competition in the retail drinking water sector. Customer segmentation using RFM (Recency, Frequency, and Monetary) analysis is one of the techniques employed. Additionally, K-Means clustering, a clustering technique based on machine learning, is employed. This study's goal is to present the findings in the form of graphs that can be used to examine consumer trends according to their attributes. With a value of 10286, the Calinski Harabaz index is a suitable metric to move on to the segmentation step in this study, which also tests three metrics using the clustering method. An ideal cluster is created for every cluster evaluation by dividing the Calinski Harabaz index into three more manageable clusters. This contrasts with other evaluation metrics that only yield two clusters. For instance, when XYZ drinking water sales transaction data was distributed, it was discovered that, out of the total drinking water sales, woodsale had 422 customers, diamond had 1061 customers, and star diamond had 2005 customers. The management of the XYZ drinking water company and other marketing fields are expected to encounter more intense competition as a result of the study's findings.

This study is based on the need to develop a more effective concentrate ration for lactating dairy cows, as existing formulations in the field are greatly influenced by the availability of ingredients and varying quality. Therefore, this study focuses on optimizing concentrate in dairy cow feed rations to meet SNI standards, which include crude protein (CP), Total Digestible Nutrients (TDN), Calcium (Ca), and Phosphorus (P), with more efficient results in terms of price and nutrition. This study uses the Whale Optimization Algorithm (WOA) metaheuristic approach, which balances the exploration and exploitation processes in finding the best solution to optimization problems. This algorithm has fewer parameters than other metaheuristics such as GA, PSO, and DE. WOA runs naturally in continuous space without the need for genetic operators such as crossover and mutation. The dataset used contains types of dairy cow feed ingredients along with nutritional requirements and prices so that researchers can process the data into efficient feed concentrate that is suitable for lactating dairy cows.

Sentiment analysis on social media is widely used to represent public perceptions of sports performance, particularly in international competitions. This study aims to analyze the sentiment of YouTube user comments regarding the performance of the Indonesian National Football Team during the FIFA World Cup 2026 Asian Qualifiers. The data were collected from user comments on videos related to the matches and analyzed using a machine learning–based sentiment analysis approach. Sentiment classification was performed using the Naive Bayes algorithm. The results indicate that the proposed approach is able to effectively identify public sentiment toward the national team’s performance during the qualification matches. The findings of this study are expected to provide insights into public perceptions and contribute to sentiment analysis research in the field of sports.