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.

Use substance chemistry in a way continously can cause accumulation residue in the soil , which is potential cause effect harm for environment . Therefore that , training intended For improve skills in groups farmer Green Lawu forest in Berjo Village , Karanganyar , in cultivation mold Trichoderma sp. as fungicide natural . Training done through method counseling that includes making starter media using Potato Dextrose Agar (PDA), and multiplication become product powder Ready use with flour media rice and bran . Training results show improvement understanding participant to benefit Trichoderma sp. , good as controller organism the bully plants (OPT) and as booster growth plants . In addition , training This succeed reduce dependence farmers on materials chemistry agriculture that is not friendly environmental and expensive. It is hoped that this program can push adoption Trichoderma sp. in a way sustainable For support system agriculture friendly environment in Berjo Village .

Dengan kemajuan teknologi saat ini, bisnis harus lebih kreatif dan inovatif dalam menjalankan operasi mereka. Sistem penjualan adalah salah satu contoh teknologi ini, yang dapat mengatur produksi dan mencatat transaksi penjualan. Usaha UMKM Nata Nugros Singkong memproduksi dan menjual produk olahan singkong seperti Gethuk Crispy, Gemblong Cotot, dan Singkong Keju. Lokasi bisnis ini adalah di Dusun Krajan, Desa Doplang, Kecamatan Bawen, Kabupaten Semarang. UMKM Nata Nugros Singkong menghadapi masalah dalam mengelola transaksi penjualan produk, memantau stok dan ketersediaan produk, dan membuat laporan dengan cara yang lebih konvensional atau berbasis kertas. Menurut pendapat kami, penerapan sistem informasi penjualan adalah langkah yang tepat untuk menyelesaikan masalah yang ada. Sistem informasi ini berbasis web menggunakan PHP dan MySQL.

The prevalence of Ear, Nose, and Throat (ENT) diseases presents diagnostic challenges, especially in resource-limited settings. At THB Bekasi Hospital, constrained specialist availability and long consultation queues highlight the need for an accessible diagnostic solution. This study aims to develop an expert system for diagnosing ENT diseases using the Extreme Programming (XP) methodology, incorporating the forward chaining technique for inference. The research includes assessment, knowledge acquisition through expert consultations, system design, and rigorous testing. The system was developed as a mobile application using Android Studio, enabling users to input symptoms and receive real-time diagnostic insights. The knowledge base integrates data from medical experts, synthesizing 11 diseases and 35 symptoms into a robust decision-making framework. The diagnostic process applies predefined rules to ensure accuracy in identifying conditions such as sinusitis, laryngitis, and otitis. Evaluation results demonstrate a 100% match accuracy during testing with 15 test cases, confirming the system’s reliability. The application offers users rapid diagnostic assistance, promoting timely treatment for ENT issues, although it does not substitute medical professionals. By leveraging ubiquitous smartphone access, this system addresses gaps in healthcare accessibility and enhances patient autonomy. This research contributes a scalable framework for deploying expert systems in other medical domains. Future improvements include integrating geolocation services for nearby specialist referrals and adopting backward chaining for more complex diagnoses, thereby broadening its applicability and utility

This research aims to analyze the types of errors made by fifth grade elementary school students in solving mathematical problems. This research uses a qualitative descriptive method with a case study approach. The research subjects were 25 students who were selected based on the criteria of various academic abilities and difficulties in problem solving. Data was collected through mathematical problem solving tests, semi-structured interviews, and observations. The research results showed that students' errors in solving mathematical problems were divided into three types, namely: conceptual errors (44%), procedural errors (36%), and calculation errors (20%). Conceptual errors occur due to students' lack of understanding of basic mathematical principles, such as fractional number operations. Procedural errors are caused by students' ignorance in determining systematic steps to solve problems. Meanwhile, calculation errors arise due to students' low accuracy and concentration. This research recommends using a problem-based learning approach and interactive media to increase students' understanding of concepts. Apart from that, providing varied practice questions and feedback can help students correct their mistakes. Thus, students' mathematical problem solving abilities are expected to increase significantly.

This research aims to implement the marketing strategy of Pempek Palembang FC (Micro, Small, and Medium Enterprises) MSMEs through Instagram social media. Established in May 2022 in Bangka Belitung, Pempek Palembang FC offers Palembang specialty food products, namely pempek and tekwan. Despite its high market potential, this MSME faces serious challenges due to its lack of social media presence, resulting in limited marketing reach. This research used qualitative methods with interviews and observations to explore the problems and solutions faced. The results show that the creation of social media accounts, creative content development, and consistency in uploading can increase visibility and sales. Through digital marketing strategies, Pempek Palembang FC can reach a wider market, build a customer community, and increase competitiveness in the digital era.
Keywords: Pempek Palembang FC, MSME, marketing strategy, social media, Instagram, digital marketing.

The aim of this research is to explore the role of parents in shaping the religious character of children through Christian Religious Education in the city. The type of research conducted is field research with a qualitative research model. The data sources used in this study include both primary and secondary data. The data collection methods employed are Observation, Interview, and Documentation. Data analysis is carried out through three stages: data reduction, data presentation, and drawing conclusions. The research findings indicate that parents play a crucial role in shaping the religious character of their children through several approaches. These include educating through behavioral examples, implementing an early education system, establishing a system of habituation, fostering a culture of dialogue between parents and children, and applying principles of justice in managing available time. Behavioral examples provided by parents have proven to be highly effective in guiding children to become useful individuals. For these behaviors to be truly effective, they must be supported by consistent policies applied across all aspects of daily life.

This research aims to design syntax in literature learning using the Project Based Learning (PjBL) model at UPT SMP Negeri 17 Medan. This research focuses on the effectiveness of applying PjBL syntax in improving students' literary understanding, critical thinking skills and creativity. This research uses a qualitative descriptive method with data collection techniques through observation, interviews and documentation. Research findings reveal that the application of the PjBL model in literature learning has a positive impact on student engagement and in-depth understanding of literary material. Project-based evaluations also help students develop collaboration and communication skills. Systematic implementation of PjBL syntax provides a clear and effective learning structure, thereby improving the overall quality of learning.

Bullying in the school environment is a problem that has a serious impact on students' emotional, social and academic development. This research aims to analyze efforts to prevent bullying behavior through a collaborative-based Pancasila and Citizenship Education (PPKn) learning approach for students at SMP Negeri 35 Medan. This research uses a qualitative descriptive method with data collection techniques through observation, interviews and documentation. The research subjects were PPKn teachers and students in grades VII and VIII of SMP Negeri 35 Medan. The research results show that collaborative-based Civics learning is effective in increasing students' awareness about the impact of bullying and strengthening positive social relationships between them. Supporting factors for implementing this method include teacher support, student enthusiasm, and school policies, while inhibiting factors include time constraints and students' lack of initial understanding about collaboration. The results of this research show that the collaborative learning approach in Civics is able to create a safe and inclusive learning environment, while preventing bullying behavior. This research recommends further development of collaborative methods involving learning technology to strengthen the results achieved.

This study focuses on strengthening brand equity in the Visual Communication Design (VCD) study program at higher education institutions by implementing interactive multimedia. The background of the problem lies in the importance of branding innovation in addressing the increasing competition in the education sector. The purpose of this research is to evaluate the impact of interactive multimedia on four dimensions of brand equity: brand awareness, brand loyalty, perceived quality, and brand associations. The methodology employed involves a mixed quantitative and qualitative approach. Data was collected through a survey of 100 respondents using a Likert-scale-based questionnaire and in-depth interviews with relevant participants. A paired t-test was used to analyze changes in brand equity perceptions before and after implementing interactive multimedia. The results show a statistically significant increase in brand awareness by 20% (p < 0.01), brand loyalty by 25% (p < 0.01), perceived quality by 18% (p < 0.01), and brand associations by 19% (p < 0.01). These findings provide practical contributions to higher education institutions by demonstrating that interactive multimedia is not merely a communication tool but an effective strategy for building emotional engagement with audiences and enhancing institutional reputation. Furthermore, qualitative insights highlight the role of interactive multimedia in fostering deeper emotional connections and improving perceptions of quality. This research supports adopting technologies like Augmented Reality (AR) and Virtual Reality (VR) to enrich future learning experiences. Continuous implementation and innovation in interactive content are also necessary to remain relevant and competitive in the dynamic education market.