Publication Search

Travel insurance provides financial protection for individuals during their trips, both domestically and internationally. With the increasing demand for travel insurance, insurance companies face challenges in efficiently managing claims. This study aims to develop a predictive model to classify whether an insurance policy will be claimed based on historical customer and transaction data. This research utilizes a dataset containing various features related to travel and policyholders, such as agent type, distribution channel, insurance product, travel duration, and premium amount. The methods used include data exploration, feature processing, and the application of machine learning algorithms such as Logistic Regression, Random Forest, and XGBoost. Experimental results indicate that the XGBoost model performs the best, achieving the highest accuracy compared to other models. With this predictive model, insurance companies can optimize claim evaluation processes, reduce fraud risks, and improve operational efficiency in handling travel insurance claims.

In the era of education that continues to develop, innovations in learning methods are very important to improve students' memory, one of which is flahcard media. Flashcard media is a medium that can help improve students' memory in a simple way so that students are interested and do not feel bored during the lesson being delivered. This study aims to determine the influence of the use of flahshcard media in the STAD learning model on student learning outcomes on atomic structure materials and the advantages of nanomaterials in class X of SMA Negeri 16 Samarinda. The type of research is Quasi Experimental Design with a nonequivalent Post-test Only Control Group Design. Class X.2 as an experimental class with the STAD learning model with flashcard media and class X.6 as a control class with the STAD learning model. The initial test was carried out first where the normality test and the t-test. The results of the t-test showed that there was no difference in absorption between the two classes. Data collection uses post tests and daily tests as well as observation sheets for teachers and students. The results of this study show that the learning outcomes of students in the experimental class and control class are obtained Sig.(2-tailed) of 0.000 < 0.05, then Ha is accepted. Based on this study, it can be concluded that there is an influence of the use of flashcard media in the STAD learning model on student learning outcomes on the atomic structure material of the excellence of nanomaterials in class X of SMAN 16 Samarinda.

Low student collaboration skills are often found in learning activities at school. This will certainly impact the low level of student learning outcomes. This study aims to examine the effect of the Learning Cycle 7E model assisted by PhET Simulation on students' collaboration skills and physics learning outcomes. This research is a true experimental study using a posttest-only control group design. The population in this study was class X students of SMK Negeri 2 Jember, while the research sample was determined using the cluster random sampling technique. Data collection methods included observation, interviews, tests, and documentation. The data obtained were analyzed using a normality test, followed by statistical tests using the Independent Sample T-test for collaboration skills and the Mann Whitney U-Test for physics learning outcomes. The results showed that the analysis of collaboration skills data using the Independent Sample T-test obtained a Sig. (2-tailed) of 0.000 ≤ 0.05, indicating a significant difference between the experimental and control groups. Meanwhile, the analysis of physics learning outcomes using the Mann Whitney U-Test obtained a Sig. (2-tailed) of 0.000 ≤ 0.05, also indicating a significant difference. Therefore, it can be concluded that the application of the Learning Cycle 7E model assisted by PhET Simulation has a significant positive effect on improving students' collaboration skills and physics learning outcomes.

The issue faced in current learning is that it is still teacher-centered, which leads to low student interest and motivation in learning. Additionally, students' attention during lessons is lacking, and they tend to get bored, resulting in poor learning outcomes. This study aims to examine the application of the Guided Inquiry learning model assisted by the Google Lens application to improve the science learning outcomes of seventh-grade students at SMP PGRI POOPO. The subjects of this study were 39 seventh-grade students in the second semester of the 2023/2024 academic year. This research utilized a classroom action research method in two cycles, each consisting of planning, implementation, observation, and reflection stages. The results of the study showed a significant improvement in student learning achievement. The classical completeness percentage in Cycle I was 52.63%, while in Cycle II, it increased to 84.21%. Based on these findings, it can be concluded that implementing the Guided Inquiry learning model supported by the Google Lens application can improve science learning outcomes for seventh-grade students at SMP PGRI POOPO. This model is expected to make students more active, interested, and motivated in learning, leading to better learning outcomes.

Customer churn is a major challenge in e-commerce, directly affecting revenue and profit. This study aims to develop a machine learning model using XGBoost to predict churn probability. To handle class imbalance, SMOTE was applied as a resampling method, and hyperparameter tuning was performed to enhance performance. The model was evaluated using the F2-score, prioritizing recall while maintaining precision. The results show that the XGBoost model with SMOTE achieves strong performance, with an F2-score of 0.849 on the tuned test data. This model can help businesses identify at-risk customers early, enabling proactive retention strategies.

Hotel booking cancellations pose significant challenges to the hospitality industry, affecting revenue management, demand forecasting, and operational efficiency. This study explores the application of machine learning techniques to predict hotel booking cancellations, leveraging structured data derived from hotel management systems. Various classification algorithms, including Random Forest, XGBoost, and LightGBM were evaluated to identify the most effective predictive model. The findings reveal that XGBoost model outperforms other models, achieving F2-score of 0.7897. Key influencing factors include deposit type, total number of special requests, and marketing segment. The results underscore the potential of predictive modeling in optimizing hotel revenue strategies by enabling proactive measures such as dynamic pricing, targeted customer engagement, and improved overbooking policies. This study contributes to the ongoing advancements in data-driven decision-making within the hospitality industry, offering insights into how machine learning can mitigate financial risks associated with booking cancellations.

This research and development is motivated by the fact that the learning of science subjects on the water cycle material is less in accordance with the characteristics of students. The limitations of teaching media in schools are educational problems that can hinder the success of the learning process. Researchers want to develop interactive science teaching materials on the water cycle material to increase the enthusiasm for learning of grade V SD/MI students. The purpose of this development research is to produce a product in the form of interactive science teaching materials in grade V on the water cycle material. This study uses the ADDIE development research model and design developed by Dick and Carry with 5 steps, namely analyzing, designing. Developing. Implementing. Evaluating. This research was conducted at MI Mifathul Huda Lamong with class V research subjects.The results of the research and development of interactive science teaching materials in grade V on the water cycle material at MI Miftahul Huda Lamong. In the development stage, the results were in the form of teaching materials developed consisting of 23 pages. This interactive science teaching material has received validity from experts (1) learning media experts of 93% with very good criteria (2) material experts of 85% with good criteria (3) student interest questionnaire of 95% with very good criteria.

This study aims to develop Nearpod learning media with a valid, practical, and effective Problem-Based Learning model for the subject of Science, especially on the material of changing the form of energy for fourth grade students of Elementary School. This research is motivated by problems found through initial observations and interviews. The method used is research and development (R&D) with the ADDIE model, which consists of five stages: analysis, design, development, implementation, and evaluation. The subjects of this study involved class teachers and fourth grade students of SDS Pelangi, while the object of the study focused on Nearpod learning media in Science learning on the material of changing the form of energy. Data collection techniques include interviews, tests, and questionnaires, with instruments in the form of teacher interview sheets, material validation questionnaires, media validation questionnaires, education practitioner questionnaires, and pretest and posttest questions. The results of the study showed that validation by material experts obtained an average percentage of 90% with the category "very feasible", while validation by media design experts obtained an average percentage of 97% with the category "very practical". Media effectiveness testing showed an increase in students' average scores from 54.73 ("quite practical" category) to 83.15 ("very practical" category) after using Nearpod media.

Speed reading is an essential skill in modern education, requiring students to quickly and effectively comprehend information. This study aims to examine innovative and effective strategies for developing students' speed reading abilities in the era of modern learning. The research method used is library research, involving an extensive review of books, scholarly journals, and previous studies relevant to speed reading instruction. The findings indicate that the most effective strategies for improving speed reading skills include a combination of skimming and scanning techniques, minimizing subvocalization, and practicing word visualization. Additionally, the integration of digital technologies, such as AI-based learning applications and interactive platforms, has been shown to enhance both reading speed and comprehension. Constructivist and cognitive learning theories also play a crucial role in developing adaptive strategies tailored to students' needs. Despite the proven effectiveness of these strategies, several challenges remain, such as low reading motivation, difficulties in maintaining focus, and limited access to technology in certain educational settings. Therefore, educators must foster a conducive learning environment and incorporate appropriate technological tools to support the development of speed reading skills. This study contributes to the development of more innovative and adaptive speed reading instructional models in the digital era. The findings are expected to serve as a reference for educators in implementing more effective strategies to enhance students' speed reading abilities.

This research investigated how using Articulate Storyline 3 within a Self-Directed Learning (SDL) model affected vocational students' motivation and physics learning achievements. The study employed a true experimental design, specifically a Post-test Only Control Group Design and was carried out at SMK Negeri 2 Jember. Sample determination is done by conducting a homogeneity test, then randomly selected for the control class and the experimental class through a lottery. Data was collected using observation, interview, questionnaire, test and documentation methods. The data analysis technique used was normality test and T test with the help of IBM SPSS 25 software. Questionnaire results indicated that students in the experimental group, who used the Self-Directed Learning model with Articulate Storyline 3, showed higher average learning motivation compared to the control group.  The results of data analysis of student learning motivation with the Independent Sample T-test test obtained a significance value of 0.010 ≤ 0.05, which means H0 is rejected and Ha is accepted. The post-test results revealed that students in the experimental group, who learned physics using the Self-Directed Learning model with Articulate Storyline 3, achieved higher average scores than those in the control group. The results of data analysis of student physics learning outcomes tested with the Mann-Whitney U-test get a significance value of 0.004 ≤ 0.05 which means H0 is rejected and Ha is accepted. So it can be concluded that there is a significant effect of the application of the SDL model accompanied by Articulate Storyline 3 media on student motivation and physics learning outcomes.

This study aims to improve students' ability to read the Qur'an fluently through interactive learning videos in the subject of Al-Qur'an Hadith at MTs Islamiyah. The method used is Classroom Action Research (CAR) with the Kemmis and McTaggart model, which consists of planning, action, observation, and reflection. The research subjects were 30 eighth-grade students. Data were collected through reading ability tests, observations, and interviews, then analyzed descriptively. The results showed a significant improvement in the ability to read the Qur'an fluently. In the pre-cycle, students' learning mastery only reached 50% with an average score of 65. After the implementation of interactive learning videos, mastery increased to 70% with an average score of 75 in the first cycle and 90% with an average score of 85 in the second cycle. This improvement was also seen in students' interest and active participation during the learning process. In conclusion, the use of interactive learning videos is effective in enhancing the ability to read the Qur'an fluently. It is recommended that teachers continue to integrate interactive learning media to improve the quality of learning, especially in the Al-Qur'an Hadith subject.

The subject of Islamic Cultural History (SKI) plays an important role in instilling Islamic historical values in students. One of the topics taught is the Story of Fathu Makkah, which describes the victory of Prophet Muhammad (PBUH) and the Muslims in conquering the city of Makkah without war. However, in the learning process of grade IV students at MI Salafiyah, it was found that students showed a lack of interest in this material due to conventional and less engaging teaching methods. This study aims to enhance students' interest in learning the Story of Fathu Makkah through the use of story posters as a teaching medium. The research method employed is Classroom Action Research (CAR) based on the Kemmis and McTaggart model, which consists of two cycles. Each cycle includes the stages of planning, implementation, observation, and reflection. Data were collected through observations, student learning interest questionnaires, and comprehension test results. The findings indicate that the use of story posters significantly increased students' learning interest. In the first cycle, students began to show interest in the material, although some were still less active. After improvements were made in the second cycle, there was an increase in student engagement during discussions, and their understanding of the material improved. Moreover, the students' average scores increased compared to before the intervention. The conclusion of this study is that the use of story posters can enhance students' learning interest in the Story of Fathu Makkah in grade IV at MI Salafiyah.

This study aims to: (1) describe the level of creativity in Grade X students at SMKS Muhammadiyah Bungoro, (2) examine the implementation of the Project-Based Learning (PBL) model in the classroom, and (3) analyze the improvement in students’ collaborative skills through PBL. The research employs a Classroom Action Research (CAR) method conducted in two cycles, each consisting of planning, action implementation, observation, and reflection. The study involved 25 Grade X students at SMKS Muhammadiyah Bungoro. Data collection techniques included observation, documentation, and interviews, with qualitative data analysis presented in percentage form. The findings indicate that: (1) students' creativity was initially low based on preliminary observations, (2) the implementation of PBL in the IPAS subject significantly enhanced students' creativity, showing improvement in all measured indicators, and (3) the PBL model also improved students' collaborative skills, increasing from 48% in the pre-cycle to 53.85% in Cycle I and 83.65% in Cycle II, surpassing the expected 80% threshold in the "collaborative" category. These findings highlight the effectiveness of PBL in fostering creativity and collaboration among students.

As a literary genre with its own appeal, short stories (qishshah qashirah) and poetry (shi'r) offer a unique and beneficial reading experience for students. However, learning to read Arabic literary texts often presents various challenges. This study aims to analyze in depth the reading skills of Arabic literary texts, specifically short stories and poetry, at Madrasah Aliyah. This research employs a qualitative descriptive method, which aims to observe and describe events, phenomena, attitudes, social activities, perceptions, beliefs, and thoughts of individuals or groups. Data collection is conducted through observation, interviews, and documentation. The data analysis technique follows the Miles and Huberman model, which consists of three main stages: data reduction, data presentation, and conclusion drawing. The findings reveal that students' ability to read Arabic literary texts, both short stories and poetry, remains relatively low. Several internal and external factors influence this ability, including limited vocabulary (mufradat), which causes students to struggle in understanding texts, frequently pause, guess word meanings, or even give up entirely. Additionally, weak proficiency in Arabic grammar (nahwu and sharaf) further hinders their comprehension of sentence structures in literary texts. To address these challenges, three strategies can be implemented by educators to enhance students' reading skills: utilizing diverse learning media, selecting engaging and relevant themes, and providing a variety of reading resources.

This study aims to develop an inquiry-based e-module as a teaching material for ecosystem topics for tenth-grade high school students. The e-module is designed to enhance student engagement in learning and foster critical thinking skills. The research method employed is Research and Development (R&D) using Sugiyono’s development model. Validation was conducted by subject matter experts, language experts, and media experts, yielding results of 86%, 93.33%, and 94.54%, respectively, all categorized as highly feasible. Practicality tests by teachers resulted in a score of 93.75%, while student practicality surveys reached 95.4%, indicating that the e-module is highly suitable for learning. The critical thinking skills test showed an overall student score average of 77.25%, classified as high. This e-module offers several advantages, including ease of access, an engaging design, and interactive content incorporating text, images, videos, and exercises. However, challenges in its implementation include limited technological access in some schools. Overall, the inquiry-based e-module is considered effective and ready for use as an alternative teaching material for ecosystem learning in high schools.

Community service is an integral part of higher education which aims to provide a positive impact on the community. The service program implemented in Binjai, Langkat Regency, aims to increase Al-Qur'an literacy among the community through the method of reciting and reciting the Al-Qur'an. This activity involves students as facilitators in guiding the reading of the Al-Qur'an, teaching Iqro, and coordinating learning with the target of completing 30 juz in nine days. The main methods applied are talaqqi and classical, which have proven effective in accelerating understanding and fluency in reading the Al-Qur'an. The results of this program show a significant increase in the ability to read the Al-Qur'an, both in terms of fluency and understanding of recitation. Apart from that, this activity also has an impact on the social aspect by strengthening relationships between community members and fostering religious enthusiasm. It is hoped that this program can become a model for increasing religious literacy in society and will continue to be developed with more sustainable innovation.

Discipline is one of the important values in the world of education that contributes to the order and responsibility of students in academic and social life. This study aims to analyze the implementation of discipline values through Dhuha prayer activities at MI Islamiyah Palangka Raya. The research method used is qualitative descriptive with data collection techniques through observation, interviews, and documentation. The results of the study show that Dhuha prayer plays a role in shaping student discipline, which is reflected in the habit of coming on time, regularity in worship, compliance with rules, and politeness and courtesy. In addition, this activity increases students' mental readiness in learning, making them more focused, patient, and enthusiastic in facing academic tasks. The role of teachers as role models and mentors is very influential in the success of this program, supported by the involvement of parents who ensure that students participate in activities consistently. Synergy between schools, teachers, and parents contributes to the sustainability of the program, so that disciplinary values can be effectively instilled. Thus, Dhuha prayer not only functions as worship, but also becomes a means of forming the discipline character of students who are responsible and have a high work ethic.

  Abstract. This study aims to determine the significant effect of the Problem Based Learning (PBL) learning model on the creative thinking skills of grade 4 students of Kleco 1 Surakarta Elementary School. This study uses a quantitative approach based on the philosophy of positivism. The population and sample used in this study were 25 grade 4 students of Kleco 1 Surakarta Elementary School. The sampling technique used was purposive sampling. This study used a One-Group Pretest-Posttest Design research design. In this design, before the treatment is given, a pre-test (initial test) is carried out, then treatment is given, and after the treatment is given, a post-test (final test) is carried out. Data collection techniques use observation, testing, and documentation. Based on the results of the study, it can be concluded that the application of the Problem Based Learning (PBL) model has a significant effect on improving the creative thinking skills of grade 4 students of Kleco 1 Surakarta Elementary School in the material of Style Around Us. This is indicated by an increase in the average value from the pretest of 54.4 to 80 in the posttest, as well as the results of the Paired Sample T-test which showed a significant difference before and after treatment.

The aim of this study was to improve students' creativity in completing Student Worksheets (LKPD) through the implementation of the Project Based Learning (PjBL) model for third-grade students at Madrasah Ibtidaiyah Mambaul Ulum Kaliacar. The research method used was Classroom Action Research (CAR) based on the Kemmis and McTaggart model, consisting of two cycles. Each cycle included the stages of planning, action, observation, and reflection. Data collection techniques involved observation, interviews, questionnaires, and documentation, while data analysis was conducted using descriptive qualitative and quantitative methods. The results of the study showed that the implementation of PjBL significantly improved students' creativity in completing LKPD in the Al-Qur'an Hadist subject. This was evident from the increase in the average creativity score of students from 65% in the first cycle to 85% in the second cycle. In addition, the level of student engagement in the learning process rose from 70% to 85%, and student satisfaction with the implementation of PjBL reached 80%. The obstacles encountered in this study included limited time and differences in students' initial abilities, but these challenges could be overcome with intensive guidance from the teacher. Thus, the implementation of Project Based Learning (PjBL) proved effective in enhancing students' creativity and learning motivation. It is recommended that teachers further optimize their roles as facilitators and consider students' characteristics to achieve more optimal results.

This research focuses on assessing the efficacy of a method that integrates Convolutional Neural Networks (CNN) with Decision Trees for the detection of phishing URLs. Phishing represents a major cyber threat, where cybercriminals attempt to deceive individuals into disclosing sensitive information via fraudulent websites. As the frequency of phishing attacks continues to rise, there is a pressing need for effective detection and prevention strategies. In this investigation, a dataset comprising both phishing and legitimate URLs was utilized to train a CNN-Decision Tree model. The training phase includes feature extraction from URLs using CNN, which excels at identifying intricate patterns within the data, followed by classification through Decision Trees, recognized for their capacity to deliver straightforward and comprehensible interpretations of classification outcomes. The model's performance was evaluated across nine distinct scenarios to assess its effectiveness under varying conditions. The results indicated that the hybrid CNN-Decision Tree model achieved a precision rate of 94%, a recall of 90%, and an F1-Score of 92%, with an overall accuracy of 93%. These findings suggest that the model is not only proficient in identifying phishing URLs but also maintains a commendable balance between precision and recall. This research highlights that the synergy of CNN and Decision Trees can serve as a potent solution for phishing URL detection, significantly contributing to the advancement of enhanced cybersecurity systems.