Publication Search

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.

This study aims to examine the effects of applying a Problem-Based Learning (PBL) method combined with PhET simulation tools on enhancing critical thinking skills among eighth-grade students at SMP Negeri 4 Singaraja when learning vibration and wave topics. It adopted a quasi-experimental approach with a Pretest-Posttest setup and non-equivalent control group design. The participant cohort comprised 75 students distributed across two groups: the treatment group (n=38) who engaged in learning activities using PBL supplemented by PhET simulation, and the comparison group (n=37) who received PBL instruction without PhET simulation support. Data collection was conducted through essay-type assessment instruments containing 7 questions designed to evaluate critical thinking competencies based on Ennis' theoretical framework. Data processing employed descriptive statistical analysis, N-Gain Score computation and ANCOVA testing were conducted at a 0.05 significance level. Results showed the treatment group's average Posttest score at 84, compared to 66 for the control group. The ANCOVA produced an F-value of 103.701 (p < 0.001), confirming a statistically significant difference in critical thinking skills between the groups. The adjusted mean Posttest scores were 83.99 for the treatment group and 66.01 for the comparison group, reflecting a differential of 17.99 points. Consequently, the findings substantiate that the integration of PBL with PhET simulation demonstrates greater effectiveness in fostering students' critical thinking skills in comparison to conventional PBL implementation without technology-enhanced simulation assistance.

This study aims to improve students’ learning outcomes through the implementation of the cooperative learning model of Student Teams Achievement Division (STAD) in the Pancasila Education subject for class VIII A at SMP Muhammadiyah Singaraja. This research employed a Classroom Action Research (CAR) design conducted in two cycles. Each cycle consisted of four stages: planning, action, observation, and reflection. The research subjects were 29 students of class VIII A. Data were collected using learning achievement tests and observation sheets. The collected data were analyzed using descriptive quantitative techniques to evaluate students’ academic progress during each cycle. The findings indicate that the implementation of the STAD learning model contributed positively to improving students’ learning outcomes, participation, and engagement in classroom activities. Therefore, the STAD cooperative learning model can be considered an effective instructional strategy for enhancing learning achievement in Pancasila Education.

This study aims to enhance the academic synergy of the Quranic Studies and Exegesis Program at IAIN Sultan Amai Gorontalo in supporting Quranic literacy mentoring activities for coastal communities in Oluhuta Village, Bone Bolango Regency. The study is motivated by the low level of Quranic literacy in coastal areas, which is influenced by limited access to religious education and a shortage of competent mentors. This condition is further exacerbated by the fact that most residents of Oluhuta Village are fishermen who spend much of their lives at sea, limiting opportunities for structured learning. Using a descriptive qualitative approach, this study explores the role of lecturers and students from the Quranic Studies and Exegesis Department in planning, implementing, and evaluating a mentoring program aimed at strengthening basic skills in reading and writing the Quran. The findings show that interdisciplinary academic synergy, particularly in tajwid, tahsin, and Quranic teaching methodologies, significantly improves participants’ Quranic literacy skills. In addition, the program strengthens the relationship between Islamic higher education institutions, particularly IAIN Sultan Amai Gorontalo, and the surrounding community. It also serves as a medium for implementing academic integration and community service values. This study recommends the development of an integrated and context-based Quranic mentoring model for similar coastal communities in other regions.

This research reconstructs the concept of the ideal human being in Aristotelian philosophy and formulates its implications for contemporary character education. The study is grounded in modern educational challenges that require not only intellectual mastery but also the cultivation of complete character based on virtue. Using library research with a hermeneutic approach, this study critically interprets Aristotle’s key concepts, particularly eudaimonia, phronesis, and virtue ethics, and contextualizes them within current educational needs. Data were collected from relevant primary and secondary literature and analyzed through thematic and conceptual analysis to identify the relationship between Aristotelian ideas and character education. The findings show that the ideal human being, according to Aristotle, is one who achieves eudaimonia through the balanced development of moral and intellectual virtues, guided by phronesis as practical wisdom. Education is therefore understood as a gradual process of character formation through habituation, experience, role modeling, reflection, and ethical deliberation. This study proposes five strategies for Aristotelian character education: virtue habituation, experiential learning, educator role modeling, ethical deliberation, and context-based integral education. The study contributes a virtue-based educational model that emphasizes wisdom, responsibility, virtue, and the realization of the good life within society.

This study was conducted to determine the best log-linear model describing the relationship between gender, sleep duration, extracurricular activities, and student learning outcomes at SMAN 1 Kualuh Hulu. A log-linear analysis approach was used to identify interaction patterns among the variables and evaluate their contribution to student academic performance. The findings showed that the selected model adequately explained the structure of the observed data. A significant three-way interaction was identified between learning outcomes, sleep duration, and gender. The results indicated that insufficient sleep duration had a negative impact on student learning outcomes, and this effect varied by gender. Female students were found to be more vulnerable to decreased academic performance caused by sleep disturbances compared to male students. Meanwhile, extracurricular activities did not demonstrate a significant direct interaction with learning outcomes. This suggests that participation in extracurricular activities was not a major factor influencing differences in academic achievement among students at SMAN 1 Kualuh Hulu.

The implementation of active learning models such as Problem-Based Learning (PBL) and Project-Based Learning (PjBL) at the junior high school level is often constrained by the complexity of instructional time management. This study aims to examine the role of the principal’s instructional leadership in addressing time management dilemmas in the implementation of active learning at SMP Negeri 6 Panyabungan. A qualitative approach with a descriptive method was employed in this study. Data were collected through non-participant observation and in-depth interviews with key informants, namely the school principal and an Islamic Religious Education (PAI) teacher selected as representatives of field conditions. The findings reveal three main results. First, teachers’ time management constraints are caused by weak control of learning activity transitions, noisy classroom conditions during group division, and low initial student learning readiness. Second, the principal implemented several concrete interventions, including the adoption of block scheduling, clinical supervision focused on classroom management, and the optimization of the Subject Teacher Forum (MGMP) or school learning community. Third, these interventions improved teachers’ instructional efficiency, strengthened classroom activity control, and created a more structured active learning process. However, sustainability challenges remain, particularly resistance from senior teachers who tend to prefer conventional teaching methods. This study concludes that adaptive and solution-oriented instructional leadership is a key factor in addressing the complexity of time management constraints in active learning implementation.

This study aims to analyze in depth the effectiveness of Realistic Mathematics Education (RME) and ethnomathematics in improving students’ mathematical abilities through a Systematic Literature Review (SLR) approach. This study is motivated by the low level of students’ conceptual understanding, mathematical literacy, and mathematical communication skills, which are still dominated by conventional teaching approaches. Data were collected from ten research articles relevant to the topics of RME and ethnomathematics. The analyzed articles employed various research methods, including experimental research, classroom action research, and research and development (R&D). The results of the review indicate that the implementation of RME is consistently effective in enhancing students’ mathematical abilities, such as critical thinking, problem-solving, mathematical communication, and mathematical literacy. The RME approach, which is based on real-life contexts, helps students understand mathematical concepts more deeply and meaningfully. In addition, the integration of culture through ethnomathematics strengthens the effectiveness of learning by providing contexts that are closely related to students’ daily lives, thereby increasing motivation, engagement, and active participation in the learning process.Furthermore, the findings reveal that the success of culture-based RME is influenced by instructional design, the selection of appropriate contexts, and the teacher’s role in managing the learning process. Therefore, culture-based RME can be considered an effective and relevant approach to improving the quality of mathematics education.

This study was conducted with the aim of explaining the influence of the project based learning model assisted by four square on the ability to write argumentative texts of class XI students of SMA Negeri 12 Semarang and its implications in learning to write. The method used in this study is a quantitative quasi-experimental approach with the nonequivalent posttest-only control group design. This design was chosen to determine the difference in the ability to write argumentative texts between students taught using the project based learning model assisted by four square and students taught with ordinary or conventional learning models. The results of the study showed that there was an influence of the project based learning model assisted by four square on students' argumentative text writing skills through the non-parametric Mann-Whitney U test of 115.500, a Z value of -4.973, and a significance value (Asymp. Sig. 2-tailed) of <0.001. Because the significance is smaller than 0.05, the null hypothesis (H₀) is rejected. It can be said that there was a significant difference between the results of the argumentative text writing test of students in the experimental class and the control class. Based on this, the application of the project based learning model assisted by four square can be used as an alternative learning model that has a positive influence on the ability to write argumentative texts of class XI students and has implications for writing learning.

This study was motivated by students’ low conceptual understanding of temperature, heat, and thermal expansion at SMP Negeri 28 Batanghari, where learning achievement remained below 50%. Instruction predominantly used PowerPoint-based media, resulting in passive learning and limited contextual engagement. This study aimed to develop web-based interactive multimedia (GlidesApps) integrated with Cepak Kapung ethnoscience that is valid, practical, and effective in improving seventh-grade students’ conceptual understanding. The study employed a Research and Development (R&D) approach using a development model consisting of five stages: analysis, design, development, implementation, and evaluation. The resulting product, named LokaSains, is a web-based learning application accessible via smartphone, laptop, or computer without installation. It presents learning content on temperature, heat, and thermal expansion integrated with the ethnoscience of Cepak Kapung, a traditional cake from Batanghari Regency. Content expert validation obtained a score of 91.07% (very valid), while media expert validation reached 87.50% (very feasible) after two revisions. Teacher practicality assessment produced 98.33% (very practical), and student responses in small-group and large-group trials reached 94% and 90.35%, respectively (very good). During implementation with 28 seventh-grade students, the mean pretest score increased from 46.07 to 76.79 in the posttest. A paired samples t-test produced t = −13.053 with Sig. (2-tailed) = 0.000 < 0.05, indicating a significant difference in conceptual understanding before and after using the multimedia. The N-Gain score of 0.57 indicated moderate effectiveness in improving learning outcomes. Accordingly, the LokaSains interactive multimedia is considered valid, highly practical, and effective for teaching temperature, heat, and thermal expansion at junior high school level.

Predictive maintenance (PdM) plays a crucial role in modern industrial systems by minimizing downtime, reducing maintenance costs, and optimizing asset performance. However, many predictive models operate as “black box” systems, limiting transparency and making it difficult for operators to interpret their outputs. This study aims to integrate Explainable Artificial Intelligence (XAI) techniques with Remaining Useful Life (RUL) prediction models to improve both accuracy and interpretability. Various machine learning and deep learning approaches, including Support Vector Machines (SVM), Random Forest (RF), XGBoost, Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN), are employed to predict RUL using real-time sensor data from rotating machinery. XAI methods such as SHAP, LIME, and attention mechanisms are applied to provide human-understandable explanations of model predictions. The models are evaluated based on accuracy, Root Mean Square Error (RMSE), and interpretability scores. The results show that XAI-enhanced models outperform traditional approaches in predictive performance while offering greater transparency. These explanations help maintenance engineers better understand the factors influencing predictions, thereby improving decision-making and trust in the system. Nevertheless, the integration of XAI introduces additional computational complexity, which may pose challenges for large-scale industrial implementation. Overall, this study highlights the potential of combining XAI with RUL prediction to develop more reliable, transparent, and effective predictive maintenance solutions.

This study aims to (1) describe the development process of the Smart Box I Obey the Rules media; (2) describe the validity of the Smart Box I Obey the Rules media; and (3) describe student responses to the Smart Box I Obey the Rules media. This study uses the ADDIE (Analyze, Design, Development, Implementation, and Evaluation) model. This research was conducted at the UPT SD Negeri 253 Gresik during the odd semester. The subjects were 25 students, 10 boys and 15 girls. Data collection techniques used included interviews, media expert validation questionnaires, material validation questionnaires, and student response questionnaires. The results of the study indicate that the Smart Box media I Obey the Rules achieved a validation result of 96,25% from media experts, categorized as very valid, a validation result of 98,75% from material experts, and a student response result of 96,8%, categorized as very good. Based on these results, the Smart Box learning media I Obey the Rules is declared valid and pravtical, making it suitable for use as a learning medium for Pancasila Rducation for first-grade elementary school students.

Education is a crucial aspect for individuals; however, in reality, many students face learning obstacles such as low motivation and academic procrastination, which can hinder their psychological development. This literature review aims to analyze the effectiveness of various Guidance and Counseling (GC) services in addressing students’ learning problems and to identify the most prevalent and efficient strategies. The research method used was a literature review of 20 scientific articles from accredited journals and academic books published over the past ten years. Data analysis was conducted thematically to map patterns and trends in the effectiveness of interventions. The results indicate that GC services significantly contribute to addressing learning difficulties through four primary models: group counseling, individual counseling, classroom guidance, and comprehensive services. Group counseling was found to be the most widely used and effective service in enhancing students’ learning motivation and social interaction through group dynamics. Meanwhile, individual counseling proved effective for addressing personal and specific issues such as truancy and procrastination. Although effective, the implementation of guidance and counseling services still faces challenges in the form of a limited number of counselors and suboptimal time management. The implications of this study emphasize the need to optimize group services as a primary strategy, as well as increased support from schools and parents to create preventive and comprehensive interventions.

This study aims to describe the implementation of the Project-Based Learning (PjBL) model in creative dance learning. It also analyzes the results of creative dance projects produced by grade XI students of SMA Negeri 14 Semarang. This study uses a descriptive qualitative approach with data collection techniques including observation, interviews, and documentation. The research subjects consist of one Cultural Arts teacher and students of grade XI. Data analysis employs the interactive model of Miles and Huberman, including data reduction, data display, and conclusion drawing. The results show that the implementation of PjBL is conducted through seven systematic stages: project determination, planning, scheduling, exploration and movement creation, monitoring, project presentation, and reflection. Students demonstrate active involvement in group discussions, movement exploration, and collaboration. Each group successfully produces creative dance work with diverse themes, reflecting the development of creativity and critical thinking skills. This study highlights students creative processes at each stage of the project, which has not been widely explored in previous studies.

This study aims to analyze the implementation of the Reconnecting active learning method in Islamic Religious Education (PAI) for ninth-grade students at SMP Negeri 2 Sentani and to examine its role in enhancing students’ learning interest and engagement. This research employs a descriptive qualitative approach with a case study design to gain an in-depth understanding of the learning process. Data were collected through in-depth interviews with three PAI teachers, the school principal, and three students, and were further supported by classroom observations and documentation. The data analysis technique used the Miles and Huberman interactive model, which includes data reduction, data display, and conclusion drawing. The findings indicate that the implementation of the Reconnecting method has a positive impact on students’ learning experiences, particularly in increasing their interest, active participation, and ability to relate learning materials to real-life contexts. Students become more responsive and motivated during the learning process. However, several challenges were identified, including limited instructional time and varying levels of teacher readiness in applying the method effectively. Therefore, continuous teacher training and better time management are recommended to optimize the use of this method in PAI learning

This literature study examines the process of self-regulation in transforming compliance with school rules originating from external pressure into behavioral regularity emerging from personal awareness, and its impact on the effectiveness of student learning outcomes. Using a qualitative approach with content analysis method, this study synthesizes relevant literature to build a theoretical framework on how self-regulation facilitates the internalization of disciplinary values. The findings reveal that self-regulation occurs through a series of interconnected stages including goal setting, strategy planning, self-monitoring, evaluation, and adjustment. The success of this process is determined by internal motivation, appropriate environmental support, positive direct experiences, and healthy emotional management. Strong self-regulation directly impacts learning outcome effectiveness through improved cognitive strategies, strengthened intrinsic motivation, enhanced time and environment management, and developed capacity to constructively cope with failure. Learning outcomes achieved through self-regulation processes are characterized by lasting understanding, knowledge transfer ability, and the formation of lifelong learning dispositions. Schools and teachers play strategic roles in strengthening self-regulation through curriculum design that supports autonomy, formative feedback, role modeling, and collaboration with parents. This study contributes theoretically by positioning self-regulation as the central mechanism bridging external influences and internal disposition formation.

Cloud job-length prediction remains challenging when the target distribution is highly skewed and contains rare extreme values. This study proposes a log-transformed, regime-based machine learning framework for robust prediction of cloud job length, represented in million instructions (MI). The approach integrates sequential feature engineering, logarithmic target transformation, weighted learning, and regime-aware modeling to distinguish between normal and extreme job-length behavior. Using an ordered GoCJ-derived cloud job-length sequence of 1000 jobs, the dataset exhibits a heavy-tailed distribution, with a mean of 129,662 MI, a median of 93,000 MI, a 95th percentile of 525,000 MI, a 99th percentile of 900,000 MI, and a skewness of 3.695. The proposed model is evaluated against sequential baselines and stronger machine learning baselines, including Naive_Last, RollingMean_5, Global_Log_ExtraTrees, RandomForest, GradientBoosting, and MLP_Log. On the main test split, the proposed Regime_Log_ExtraTrees achieved the best RMSE of 206,255.66 and the least negative R² of −0.01062, while Global_Log_ExtraTrees remained competitive in terms of MAE, MedAE, and RMSLE. Additional walk-forward validation confirms that the regime-aware model consistently achieves the best mean RMSE and mean R² across temporal folds. Ablation results further show that regime-aware learning is the primary contributor to robustness, although accurate prediction of extreme jobs remains challenging. These findings indicate that log-transformed, regime-based learning provides a practical and more robust strategy for cloud job-length prediction under heavy-tailed workload conditions.

The importance of education as a foundation for developing an intelligent and qualified generation, with an emphasis on Islamic religious education as a tool for shaping students' character and morals. Islamic religious education, particularly in the study of faith and morals, emphasizes ethical values ​​such as caring and honesty. With the challenges in education becoming increasingly complex, one example is that many educators are unable to utilize learning media in today's advanced technology. One proposed solution is the use of the digital platform Kahoot, which has been proven to attract student interest in learning faith and morals, overcoming the boredom often encountered with traditional methods, such as lectures. It is emphasized that schools need adequate facilities and strategies for using gadgets to enhance students' learning experiences.The quantitative method used in this study is a pre-experimental study. In this study, the researcher used the one-group pretest and posttest design model. Based on the research results, there was a pretest score with a mean of 93.46, a median of 95, and a mode of 95. The posttest score had a mean of 84.62, a median of 90, and a mode of 100. The sig. (2-tailed) table showed 0.002 with a research alpha of 5% or 0.005. It can be concluded that there is no effect because 0.002 < 0.005. Therefore, H1 is rejected. Therefore, there is no effect of using the Kahoot application on the subject of faith and morals on improving student learning outcomes at MAS Tarbiyah Islamiyah.

This study explores the dynamics of children’s character formation within Christian families in the digital era from the perspective of church parents. Employing a descriptive light mixed-methods design, the study integrates survey data and semi-structured interviews to obtain both quantitative and qualitative insights. The findings indicate that digital media has become an integral and unavoidable part of family life, making children’s character formation highly dependent on parental guidance, reflective communication, and consistent faith-based education at home. Parents face various challenges related to time constraints, limited digital literacy, and the increasing exposure of children to external values that may not align with Christian teachings. At the same time, many parents actively utilize technology as a supportive and accessible tool for spiritual learning and moral development. The study concludes that character formation is shaped not merely by technology itself but more significantly by the quality of family relationships and parental role modeling grounded in Christian values. Therefore, the findings recommend strengthening faith-based digital literacy among parents and enhancing church–family collaboration to foster more holistic, balanced, and sustainable character development in children.

This study aims to improve student engagement and learning outcomes in the subject of Natural and Social Sciences (Ilmu Pengetahuan Alam dan Sosial / IPAS) through the implementation of the Auditory, Intellectually, Repetition (AIR) learning model in a fourth-grade elementary school class. The initial problem indicated that student engagement in learning was still low, at 37.5%, with learning mastery reaching only 33.3% and an average class score of 68.0, which did not meet the Minimum Mastery Criteria (KKM) of 75. Therefore, improvement efforts were needed through the implementation of a more active and student-centered learning model. This study employed a Classroom Action Research (CAR) approach conducted in two cycles, where each cycle consisted of planning, action, observation, and reflection stages. The research subjects were 24 fourth-grade students. Data collection techniques included observation of student engagement, learning outcome evaluation tests, field notes, and documentation. Student engagement data were analyzed using percentages, while learning outcomes were analyzed through mean scores and the percentage of classical learning mastery. The results showed a significant improvement in each cycle. In Cycle I, student engagement increased to 62.5%, with learning mastery reaching 54.17% and an average score of 74.29, although it had not yet achieved classical completeness. In Cycle II, student engagement increased to 87.5%, with learning mastery reaching 100% and an average score of 85.42. These improvements indicate that the implementation of the AIR model was able to gradually and sustainably enhance both the learning process and outcomes. Based on these findings, it can be concluded that the Auditory, Intellectually, Repetition (AIR) learning model is effective in improving student engagement and learning outcomes in IPAS. This model can serve as an alternative learning strategy to create a more active, systematic, and student-centered learning environment.