Publication Search

This study explores the application of machine learning algorithms, specifically Linear Regression and Decision Tree Regressor, for predicting student academic performance using academic grade data from Kaggle. The analyzed factors include attendance, assignment grades, midterm exam grades, and final exam grades. The research methodology encompasses data collection, preprocessing, model development, training, and validation. This study contributes to the field of educational data analytics by demonstrating how machine learning can provide actionable insights into students' learning patterns and academic outcomes. The findings emphasize the effectiveness of Linear Regression for linearly distributed data and Decision Tree Regressor for capturing complex, non-linear relationships. The implications of this research suggest that machine learning models can assist educators in identifying key factors influencing student performance, enabling targeted interventions to enhance learning outcomes. Future research should explore larger, more diverse datasets and incorporate ensemble methods, such as Random Forest or Gradient Boosting, to improve model generalization and prediction accuracy. Additionally, integrating socio-economic and psychological factors could provide a more holistic perspective on academic achievement.

This research is motivated by the low problem solving skills of students in Natural and Social Sciences subjects. The purpose of this study was to determine the improvement of students' problem solving skills in Natural and Social Sciences subjects through the application of the Predict Observe Explain learning model. Researchers used a class action research method with the research subjects, namely the fourth grade homeroom teacher and 23 fourth grade students. Research activities were carried out for two cycles and each cycle consisted of two meetings. Data collection techniques using observation techniques, tests, interviews and documentation. While data analysis techniques using qualitative and quantitative data analysis. Based on the results of the study, it shows that the application of the Predict Observe Explain learning model can improve problem solving skills. This improvement can be seen in the activities that have been carried out for two cycles, namely the action in cycle I, the average student problem solving skills increased to 53.71% in the moderate / sufficient category. Then in cycle II, the average student problem solving skills increased to 77.21% in the high / good category. It can be concluded that through the application of the Predict Observe Explain learning model in Natural and Social Sciences subjects can improve the problem solving skills of fourth grade students of Asy-Syifa Integrated Islamic Elementary School Jambi City.

This study aimed to analyze the influence of training and development, employee engagement, learning culture on employee performance at Yogya Group PT. Akur Pratama Regional Priangan Timur, as well as the role of learning culture in moderating the relationship between training, development, and employee engagement on employee performance. This research used a survey method with a quantitative approach, involving 175 staff and supervisors. Data analysis was conducted using Partial Least Square-Structural Equation Model (PLS-SEM), which proved that training and development, employee engagement, and learning culture had a positive and significant influence on employee performance. Learning culture also strengthened the relationship between training, development, and employee engagement on employee performance.

This study aims to describe the strategies used by PPKn teachers of grade VII at MTs Negeri Samarinda in fostering students' disciplined character during learning. This study uses a qualitative research type with research subjects consisting of 1 PPKn teacher of grade VII and 6 students of grade VII through the stages of observation, interviews, and documentation. The results of the study indicate that the development of disciplined character carried out by PPKn teachers went well where the teachers implemented various strategies, namely: Development of discipline in dressing is carried out through role models, conditioning at the beginning of learning, and giving sanctions. Development of time discipline is carried out through role models, giving tiered sanctions, and arranging activities and duration of activities in the classroom according to estimates. Development of task discipline is carried out by giving assignment deadlines, clear assignment guidelines, and feedback on student assignment results. Meanwhile, development of behavioral discipline is carried out through role models, setting behavioral rules during learning, and giving tiered sanctions. During the implementation of the above strategies, it was seen that students had shown their discipline well.

Education is a key factor in human resource development, especially in rural areas that often face challenges in accessing quality education. The Afternoon Tutoring Program (Bimbel Sore) conducted by KKN-MAS students from Universitas Muhammadiyah Prof. Dr. HAMKA in Sidorejo Village aims to enhance elementary school students' academic understanding and learning motivation. This program was attended by 30 students and focused on core subjects such as Mathematics, Indonesian Language, and Natural Sciences using an interactive approach, including group discussions, quizzes, and Q&A sessions. Evaluation results showed an increase in students' comprehension, with an average score improvement of 25%, as well as greater active participation in learning. Furthermore, the program contributed to boosting students' confidence in facing academic challenges. This initiative is expected to serve as a model for improving education quality in rural areas and inspire other community service activities. The sustainability of this program can be strengthened by involving more volunteers and expanding the range of taught materials to better align with students' needs in the future.

Improving the quality of educational services is a crucial aspect in ensuring effective learning and equitable access for all students. However, many schools still face challenges in strategic planning due to the lack of systematic data utilization in decision-making. This study employs a qualitative method with a case study approach at SMP Al Furqon and SMP Asy Syafaah in Jember Regency, which implement Data-Based Planning (PBD) through the Identify, Reflect, and Improve (IRB) method. Data collection was carried out through interviews, observations, and document analysis related to the implementation of PBD in schools. The findings indicate that the implementation of PBD contributes to improving school management effectiveness, student academic achievement, and the satisfaction of educators and parents. Schools that apply PBD can allocate resources more efficiently based on measurable needs analysis. Additionally, schools with better data management systems tend to identify and address educational issues more quickly. This research contributes to strengthening data-driven education policies to enhance the quality of school services sustainably and provides a strategic implementation model for other schools seeking to adopt a similar approach.

Learning interest is one of the key factors influencing students' success in understanding a subject. In reality, many students struggle to engage with Natural Science (IPA) lessons due to less interactive and conventional teaching methods. The Team Games Tournament (TGT) cooperative learning model is an approach that can be used to enhance students' interest in learning through engaging games and academic competitions.This study aims to increase the learning interest of third-grade students at SD GMIT Nenu in Natural Science (IPA) by implementing the TGT method. The research employs a Classroom Action Research (CAR) method, conducted in two cycles, each consisting of planning, implementation, observation, and reflection. The research subjects were 16 third-grade students at SD GMIT Nenu in the 2022/2023 academic year. Data collection techniques included observations, learning interest questionnaires, interviews, and learning outcome tests. The collected data were analyzed using qualitative and quantitative descriptive techniques.The results indicate that the implementation of the TGT method significantly increased students' learning interest. Before the intervention, only 45% of students demonstrated a high interest in learning, with an average test score of 65.0. After applying the TGT method in the first cycle, learning interest increased to 75%, and the average student score improved to 80.5. In the second cycle, students' learning interest reached 93.75%, with an average score rising to 98.12. These findings demonstrate that the TGT method makes learning more engaging, fosters student interaction, and helps them understand scientific concepts more effectively.Based on these findings, it can be concluded that the TGT cooperative learning method is effective in enhancing elementary school students' learning interest. Teachers are encouraged to adopt this method for teaching Natural Science or other subjects that require active student participation. Furthermore, future research can be conducted to explore the effectiveness of this method in higher education levels and in different classroom settings.

This research aims to conduct a bibliometric analysis of literature discussing the experience of using the project-based learning (PjBL) model in creative and entrepreneurship education. The method used is descriptive bibliometric analysis. The research results show increasing interest in PjBL in education, influenced by changes in the curriculum which emphasize project-based learning experiences and the role of technology in facilitating learning. PjBL not only improves technical skills but also soft skills such as communication, collaboration and time management, which are much needed in the modern world of work. The integration of technology in PjBL enables more interactive and interesting learning, increasing student engagement and motivation. In addition, this research highlights the importance of collaboration between researchers, educators and practitioners in developing learning models that are effective and relevant to the needs of industry and society. With a better understanding of user experiences in the PjBL context, learning practices can be developed more effectively to prepare future generations to face global challenges with creativity and confidence

One of the main problems in learning today is the low absorption of students because the quality of the learning process has not been able to create a quality learning process. In this case the teacher uses the CTL learning model. The purpose of this study is intended to reveal more deeply related to the implementation of the contextual teaching and learning (CTL) learning model in improving the quality of PAI learning at SMP Muhammadiyah 9 Kota Bandung , with a research fokus. (1) Planning of the Contextual Teaching and Learning (CTL) model in improving the quality of PAI learning at SMP Muhammadiyah 9 Kota Bandung, (2) The quality of PAI learning as the output of the implementation of the Contextual Teaching and Learning (CTL) model at SMP Muhammadiyah 9 Kota Bandung. This research uses a qualitative approach, the type of case study research. Data was collected by means of interviews, observation and documentation. Data analysis was carried out through data reduction, data presentation and conclusion drawing. The research results show that: (1) Planning of the Contextual Teaching and Learning (CTL) Model, there are three stages; first, introduction: KD suitability with methods, materials and models, choosing learning media and learning resources. second, implementation: the student center learning process through the stages of constructivism, inquiry, questening, learning community, modeling, reflection, authentic assessment. third, the teacher evaluates the students through authentic assessment. (2) The quality of PAI learning as the output of the implementation of the Contextual Teaching and Learning (CTL) model at SMP Muhammadiyah 9 Kota Bandung. First, teacher learning behavior (building students' positive attitudes towards learning). Second, the behavior and impact of student learning (able and willing to expand knowledge of skills and fortify their attitudes). Third, the learning climate (a climate that is conducive to the development and improvement of curious learning activities). Fourth, learning materials (there is an adjustment between the breadth and depth of the material and the time available). Fifth, learning media (able to improve student learning experience).

spam is posting unsolicited messages or advertising on social media, particularly Twitter. These messages are normally designed to sell specific products and services or links. In this research, we developed a fuzzy control system to detect Arabic spam tweets based on deep learning with a large language model. Initially, we performed text cleaning and further transformed text into vectors with the help of AraGpt and AraBert. Subsequently, we employed a multi-layer perceptron network model in feature extraction of essential features. Finally, we adopted the fuzzy logic control system for classifying spam tweets using features filtered from deep networks. Employing the proposed Fuzzy logic control system provided nearly a 100% comparative to only utilizing the deep neural networks, which yielded an almost 99% throughput for both large language models Aragpt and Arabert, with a 100% F1 score for the Aragpt model and 99% for Arabert model respectively.

Many students have difficulty in learning mathematical concepts, especially in the material of curved-sided spatial figures, in addition, knowledge of regional culture is still lacking. This is due to the limited use of teaching materials in learning which has an impact on students' interest in learning. The purpose of this study is to develop teaching materials in the form of e-modules with an ethnomathematics approach to curved-sided spatial figures that are suitable for use, as an alternative to other teaching materials that can be used in learning. The type of research method used is the Research and Development (R&D) method with a 4D development model (Define, Design, Develop, Disseminate). The subjects of this study were grade IX students at SMPN 2 Kaledupa. The instruments used to measure the validity and practicality of the teaching materials developed were in the form of a validation questionnaire from material experts and media experts and a student response questionnaire. The data obtained from measuring validity and practicality were then processed using quantitative and qualitative descriptive analysis. The results of the research on the development of teaching materials with an ethnomathematics approach show that the developed learning e-module is declared feasible to use based on the assessment results of the material expert and media expert validators. The average score percentage obtained from the material expert validator is 89.06% with very valid criteria. While the average score percentage from the media expert validator is 86.45% with very valid criteria. In addition, the learning e-module with an ethnomathematics approach is also declared practical to use based on the results of the student response assessment. The average percentage of the overall student response assessment score is 89.93% with very practical criteria.

Advances in information and internet technologies have significantly transformed the business environment, including the financial sector. The COVID-19 pandemic has further accelerated this digital adoption, expanding the e-commerce industry and highlighting the necessity for secure online transactions. Credit Card Fraud Detection (CCFD) stands critical as the prevalence of fraudulent activities continues to rise with the increasing volume of online transactions. Traditional methods for detecting fraud, such as rule-based systems and basic machine learning models, tend to fail to keep pace with fraudsters' evolving tactics. This study proposes a novel ensemble deep learning-based approach that combines Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Multilayer Perceptron (MLP) with the Synthetic Minority Oversampling Technique and Edited Nearest Neighbors (SMOTE-ENN) to address class imbalance and improve detection accuracy. The methodology integrates CNN for feature extraction, GRU for sequential transaction analysis, and Multilayer Perceptron (MLP) as a meta-learner in a stacking framework. By leveraging SMOTE-ENN, the proposed approach enhances data balance and prevents overfitting. With synthetic data, the robustness and accuracy of the model have been improved, particularly in scenarios where fraudulent examples are scarce. The experiments conducted on real-world credit card transaction datasets have established that our approach outperforms existing methods, achieving higher metrics performance.

Analysis of the preliminary research phase as the basis for developing a biology practicum guide based on a scientific approach. The purpose of this study was to describe the initial research stage data obtained as a basis for developing teaching and learning materials based on research results that will be made in the future. The development model applied in this study is the Plomp model, which has reached the initial data investigation stage. Instruments for collecting data include interviews, observations, and questionnaires. The results of the student needs questionnaire revealed that students agreed that it was necessary to develop a practicum guide based on a scientific approach with a percentage of 94.73%. The teaching materials that have been used in learning are less effective so that students are less able to understand the subject matter. So it can be concluded that it is necessary to develop teaching materials for practicum guides based on a scientific approach on the material of the circulatory system and respiratory system in class XI SMAN 15 Pekanbaru.

This study aims to determine the procedure for the development, form, and feasibility of news text teaching materials for grade VII students. This research uses a research and development (R&D) method with a model developed by Borg and Garl that has been modified by Sugiyono and designed according to the needs and limitations of this research. The stages carried out in this research process are a) potential and problem analysis, b) data collection, c) product design, d) design validation, and e) design revision. Product assessments are carried out by two experts, namely material experts and media experts. The results of the study show that (1) The teaching material of news texts for grade VII students is developed in the form of a book with learning outcomes, namely the ability to write ideas, thoughts, views, directions, or written messages for various purposes logically, critically, and creatively. (2) The results of the validation of material experts show that with an average score of 84% with the criteria of "very good". Furthermore, the results of the validation of media experts with an average score of 95.38% with the criteria of "very good". Therefore, from the results of the research that has been carried out, it can be concluded that the teaching materials developed are valid with a status that is suitable for use with very good criteria and can be used as teaching materials to support learning in the news texts of grade VII students.

This article is about the importance of learning motivation, which serves as an effort to achieve achievement. In teaching and learning, motivation is a very important factor because it can foster students' interest in learning. Students with strong motivation will have the energy to carry out learning activities. The lack of learning motivation in Aqidah Akhlak lessons at MA PLUS SUNAN KALIJAGA class XI A has resulted in unsatisfactory learning outcomes, falling below the Minimum Completion Criteria (KKM). Thus, students' learning outcomes are less successful because the average score is lower than the KKM, due to the use of conventional methods. Therefore, a learning method that can make students learn with enthusiasm and more meaning is needed, namely the brainstorming learning method. The purpose of this study is to determine the effectiveness of applying the brainstorming method to improve students' learning motivation. The author applies classroom action research with the model from Kemis and McTaggart, which consists of four components: planning, acting, observing, and reflecting. This study shows that the application of the brainstorming method can improve students' learning motivation.

The mathematics learning process at high school level often faces challenges in terms of difficulties in understanding concepts. Conventional learning media is not interesting and interactive enough so it is less effective in understanding the material. This research aims to produce learning media using PowerPoint on the subject of statistics for class X. The development model used is the R&D model with the ADDIE development pattern, which consists of five stages: analysis, design, development, implementation and evaluation. The data collection technique used was a questionnaire. Data collection instrument that will obtain quantitative and qualitative data. Qualitative data was obtained from suggestions and input, while quantitative data was obtained from questionnaire calculations. The data analysis technique used is validation data analysis and learning media practicality data. The results of research validation analysis by three validators, namely media experts, material experts and learning experts using a Likert scale, show that the average validation of learning media is in the very feasible category. Apart from that, the results of the analysis of student response questionnaires, which involved thirty-two students, showed that the learning media obtained an average that fell into the very practical category. The conclusion of this research is that the interactive PowerPoint learning media on the subject of statistics, the material focusing on single data, has been tested and proven to be very feasible and very practical.”

This classroom action research aims to increase students' interest in learning in class XIC MA Plus Sunan Kalijogo for the 2023/2024 academic year in the subject History of Islamic Culture (SKI) through demonstration learning methods. This research was conducted in class XIC, totaling 23 students, based on a lack of interest in learning SKI because students felt bored and sleepy. This classroom action research was divided into two cycles. Data collection takes the form of observations, interviews and written tests. The results of the research show that there is a development of students' interest in learning which is characterized by increased student activity in asking questions, stable student attendance, and increased grades. In cycle 1 the percentage of student attendance reached 96 percent, and in cycle 2 it reached 97 percent. Apart from that, the average student score also increased, in cycle 1 the average student score was 75,6, and in cycle 2 the average student score was 79,1. With the existing data, it can be concluded that the demonstration method can increase students' interest in learning SKI in class XIC MA Plus Sunan Kalijogo Pogalan Trenggalek.

In order to improve the quality of education, speaking skills are one of the important aspects that students need to have. However, in reality the speaking skills of class IV students at State Elementary School 67 are still low. Therefore, this research aims to improve students' speaking skills through the application of role-playing methods. This research uses the Kemmis and McTaggart model which consists of four stages, namely planning, action, observation and reflection. In this way, it is hoped that students' speaking skills can improve and become more effective in communicating. Based on the results of observing teacher activities in cycle I, results were obtained with a percentage of 75%, then in cycle II teacher activity increased to 92% with very good qualifications. Meanwhile, the results of observing student activities in cycle I obtained a result of 73.73% and increased in cycle II to 88% with very good qualifications. Based on these data, it shows that there has been an increase in teacher and student activity in implementing role-playing methods in the learning process. Thus it can be concluded that the application of the role playing method is able to improve students' speaking skills in learning Indonesian for class IV students at State Elementary School 67.

Predicting credit worthiness is an important step for banks to reduce the risk of bad credit. This research compares the performance of four classification algorithms, namely SVM, Naïve Bayes, Random Forest and Decision Tree using simulated datasets. The results obtained on the metrics of accuracy, precision, recall, F1 score, and AUC-ROC, show that Decision Tree has the best performance with 42.5% accuracy, 48.3% precision, 47.5% recall, 47.5% F1 score, and AUC 0.60, indicating its ability to is in differentiating credit worthiness. Random Forest achieved an accuracy of 37.5% and an AUC of 0.493, while Naïve Bayes had the lowest accuracy with an accuracy of 27.5% and an AUC of 0.425. SVM gives better results than Naïve Bayes but is still inferior to Decision Tree. This research recommends implementing a Decision Tree as the main model with optimization through hyperparameter tuning, adding relevant features, and handling data accounting. These results are expected to support banking decision making more effectively and efficiently.

Education plays a very strategic role in forming a harmonious society, especially in the context of cultural, religious, and social diversity. This study focuses on the role of education in building an attitude of tolerance in the formal education environment. Using a literature study approach, this study explores various theories and previous research results to understand the relationship between education and tolerance. The results of the analysis show that education not only functions as a means of transferring knowledge, but also as a medium for forming character and moral values. Inclusive religious education and a collaborative approach to learning have proven effective in instilling diversity values. However, this study also found various challenges, such as the lack of integration of tolerance values ​​in the curriculum, social stereotypes, and the influence of a less supportive family environment. To overcome these obstacles, a strategy is needed that involves teacher role models, active family participation, and curriculum updates that emphasize character education more. This study is expected to be a theoretical contribution in understanding the role of education as the main instrument for forming a tolerant and inclusive society.