Publication Search

This study aims to analyze the influence of pocket money and Islamic financial literacy on student consumption behavior at SMAS AL-KAHFI Islamic Boarding School. The research background is based on the importance of students' understanding of personal financial management, especially in the context of pesantren based education that integrates sharia values. The research method used was quantitative with a multiple linear regression approach to test the relationship between free variables (sharia allowance and financial literacy) and bound variables (consumption behavior). The population in this study is all students of SMAS AL-KAHFI which is 675 people. A sample of 60 students was selected using the Hair et al. formula, with data collection techniques through questionnaires as primary data sources and literature studies as secondary data. Data analysis is carried out with the help of statistical software to test the validity, reliability, and significance of relationships between variables. The results of the study show that simultaneously, pocket money and Islamic financial literacy have a significant influence on students' consumption behavior. Partially, allowances have a positive and significant effect, showing that the larger the allowance received, the higher the tendency of students to consume. Meanwhile, Islamic financial literacy has a positive but insignificant effect, which indicates that understanding of Islamic finance principles has not fully affected students' consumption patterns in real terms. A determination coefficient of 85.5% indicates that both independent variables are able to explain most of the variation in students' consumption behavior, while the rest are influenced by other factors outside the model. This research contributes to the development of Islamic finance education in the pesantren based school environment and becomes the basis for wiser management of pocket money among students.

This study aims to describe in depth the role of guidance and counseling (BK) in improving the effectiveness of consultation and collaboration services at SMA Negeri 3 Tasikmalaya City. Consultation and collaboration services are an integral component of the BK program that focuses on professional interactions between BK teachers and various related parties, such as subject teachers, homeroom teachers, parents, and other stakeholders who are concerned about student development. Through these services, BK teachers help students overcome personal, social, and academic problems holistically. This study used a qualitative approach with descriptive methods. Data were collected through in-depth interviews, participant observation, and documentation analysis to obtain a comprehensive picture of the consultation and collaboration practices implemented. The data analysis process was carried out thematically to identify interaction patterns, forms of collaboration, and supporting and inhibiting factors in the implementation of services. The results show that BK teachers at SMA Negeri 3 Tasikmalaya City play an active role as a communication liaison between students, teachers, and parents, as well as mediators in solving problems faced by students. Effective collaboration between BK teachers and all related parties contributes to the creation of a conducive, inclusive, and responsive learning environment to students' needs. Consultation services implemented in a planned, continuous, and data-driven manner can provide a better understanding of student problems and offer appropriate and applicable alternative solutions. These findings confirm that guidance and counseling play a strategic role in supporting educational success in schools. The implementation of effective consultation and collaboration services not only positively impacts student problem-solving but also strengthens synergy between educational elements in building a supportive school climate oriented toward student well-being.

The rise in corruption cases in Indonesia significantly hampers investment, impacts national economic growth, and undermines the integrity of public institutions. This study highlights the strategic role of public mobilization as guardians of transparency in preventing potential corruption at the Danantara Investment Management Agency (BPI). Using a normative legal research approach enriched by qualitative analysis of the regulatory framework and best practices, this study examines the legal basis supporting public participation and formulates an effective corruption prevention strategy in the digital era. The results show that optimizing the role of the public through information transparency and the use of information and communication technology (ICT) plays a crucial role in building accountability and detecting irregularities. Access to audit data, financial evaluations, and public information is an important instrument in strengthening oversight. The use of ICT allows the public to analyze anomalous patterns, assess institutional performance, and provide constructive feedback on investment management policies. However, this mobilization faces significant challenges. First, the complexity of financial and regulatory data often makes it difficult for the general public to interpret. Second, limited digital literacy hinders the public's ability to utilize oversight technology. Third, the urgent need for certainty of legal protection for whistleblowers or oversight participants is a determining factor in the success of the mobilization. Therefore, strengthening regulations that guarantee legal protection, increasing digital literacy capacity, and developing user-friendly public oversight platforms are necessary. Synergy between the government, investment management institutions, and the public is key to creating a transparent, responsive, and adaptive oversight system to technological developments. This way, the active role of the public can be optimized to strengthen the integrity of BPI Danantara and promote a healthy investment climate in Indonesia.

This study addresses the issue of unit delays in providing goods receipt notes and routine distribution of supplies to the general logistics department, which impacts the inefficiency of the non-medical logistics management process at Ibnu Sina General Hospital, Bukittinggi. Untimely logistics management can hamper the availability of goods, disrupt the smoothness of services, and increase the risk of stock outs. The purpose of this study is to obtain a comprehensive overview of non-medical logistics management at the hospital, particularly in the aspects of planning, procurement, and control. The research method used is descriptive qualitative with in-depth interviews with five informants. The research informants include Mrs. D as triangulation, Mr. Y and Mr. B as general logistics staff, and Mrs. D and Mrs. S as unit staff. Data were analyzed to identify patterns and obstacles that occur in the non-medical logistics management process. The results show that the entire non-medical logistics management process at Ibnu Sina General Hospital, Bukittinggi is guided by requests from the unit. Logistics planning is carried out based on the receipt notes submitted by the unit, procurement can only be carried out after the receipt notes are received, and stock control is carried out by summarizing requests in the stock card. Although the procedures complied with the Standard Operating Procedures (SOPs) established by the hospital director, obstacles were identified, including delays in unit submissions and weak stock control at the unit level. This situation has the potential to lead to management inefficiencies and stockouts. The conclusion of this study confirms that the non-medical logistics management system at Ibnu Sina Islamic Hospital, Bukittinggi, complies with SOPs. However, improvements in timeliness in submitting orders and strengthening stock control within the units are needed to optimize logistics management efficiency.

The shift in lifestyle patterns, particularly in urban areas, has driven rapid growth in the fast food industry in Indonesia. Many franchise businesses are chosen by the public because they offer proven systems that reduce the risk of failure. This study aims to analyze and examine the market expansion strategies implemented by fast food franchise brand owners in Indonesia. The focus of this study is a descriptive qualitative approach with case studies of several local and international fast food franchises. The methods used in this study include in-depth interviews, observation, and documentation to gather relevant data on the strategies employed. Successful franchises are influenced by several key factors, including strong brand equity, clear operational standards, and support systems provided by the franchiser to franchisees. Furthermore, the ability to adapt to local tastes is also an essential aspect in the success of expanding fast food franchises in Indonesia. The study also reveals that the utilization of digital media, selection of strategic locations, and partnerships with food delivery services are major drivers of market expansion strategies. The results of this study emphasize that fast food franchises looking to grow further need to implement product differentiation strategies to remain competitive in an increasingly crowded market. Product innovation is key for franchises to stay relevant and stand out from other brands. Additionally, continuous mentoring and evaluation of franchise partners are critical for ensuring sustainable and mutually beneficial collaborations. Overall, applying the right strategies and ensuring sustainability will ensure the success and broader market expansion of fast food franchises in Indonesia.

Electricity has emerged as an essential requirement in modern life. As demand escalates, electricity costs rise, making wastefulness a drain on financial resources. Consequently, forecasting electricity usage can enhance our management of consumption. This study presents an IoT-based monitoring and forecasting system for electricity consumption. The system comprises two NodeMCU micro-controllers, a PZEM-004T sensor for collecting real-time power data, and three relays that regulate the current flow to three distinct electrical appliances. The data gathered is transmitted to a web application utilizing the k-Nearest Neighbor (k-NN) algorithm to forecast future electricity usage based on historical patterns. We evaluated the system's performance using four weeks of electricity consumption data. The results indicated that predictions were most accurate when the user’s daily consumption pattern remained stable, achieving a Mean Absolute Error (MAE) of approximately 1 watt and a Mean Absolute Percentage Error (MAPE) ranging from 1% to 1.7%. Additionally, predictions were notably precise during the early morning hours (3:00 AM to 8:00 AM) when k=6 was employed. This study demonstrates the effectiveness of integrating IoT-based systems with machine learning for real-time energy monitoring and forecasting. Furthermore, it emphasizes the application of data mining techniques within embedded IoT environments, providing valuable insights into the implementation of lightweight machine learning for smart energy systems.

The management of blood glucose levels in individuals diagnosed with diabetes mellitus is a multifaceted process that involves the integration of pharmacological therapy and evidence-based nutritional interventions. Among these strategies, nutritional therapy plays a pivotal role in achieving optimal glycemic control and preventing diabetes-related complications. The success of nutritional therapy is closely tied to the individual’s adherence to prescribed dietary guidelines and the ability to meet adequate protein intake as recommended by healthcare providers. Protein is essential not only for maintaining muscle mass and supporting metabolic functions but also for its role in stabilizing blood glucose levels through slower glucose absorption and enhanced satiety. This study was conducted to investigate the relationship between dietary adherence and adequate protein intake with fasting blood glucose (FBG) levels among outpatients diagnosed with type 2 diabetes mellitus at RSUD dr. Iskak Tulungagung. A quantitative research method with a cross-sectional design was employed, involving 26 respondents selected using a non-probability sampling technique. Data collection utilized structured questionnaires to assess dietary compliance, interview forms to capture dietary behavior and protein intake patterns, and medical record documentation to obtain accurate FBG measurements. Statistical analyses included Pearson correlation tests for normally distributed data and Spearman rho tests for non-normally distributed data, ensuring appropriate analytical rigor. The results indicated a significant negative correlation between both dietary adherence and adequate protein intake with fasting blood glucose levels. This finding suggests that individuals who consistently follow dietary recommendations and consume sufficient protein tend to exhibit lower FBG values, indicating better glycemic control. Such results underscore the importance of not only emphasizing dietary compliance but also ensuring protein adequacy in daily nutritional plans for type 2 diabetes patients. These findings have practical implications for diabetes management programs, highlighting the necessity of sustained patient education, regular counseling, and individualized meal planning.

Mathematics is a universal science that underlies the development of modern science and technology, and has an important role in the development of human thinking. Mathematics is a subject that is based on logical, rational, critical, and systematic thinking patterns. Religion and rationality are two perspectives that have a strong influence. Humans view religious values ​​and rational values ​​as different entities, causing a dichotomy paradigm, especially in the realm of education. In the perspective of the epistemology of science in Islam, Islam and science are complementary and interdependent entities. The mathematical approach used here does not mean that Islamic values ​​are low, but only to increase the belief of Muslims that all knowledge is valuable and can lead to true goodness and increase faith and closeness to Allah SWT.To examine how Islamic values ​​are applied in mathematics learning, To identify and develop effective strategies or methods in integrating Islamic values ​​in mathematics learning materials, To measure the extent of the application of Islamic values ​​in mathematics learning.This study uses a qualitative approach, while the type of research used by the researcher is descriptive research.Mathematics as a logical and systematic science, has a meeting point with Islamic teachings that emphasize truth, justice, and balance. For example, the concept of monotheism can be associated with the order of the universe expressed through mathematical formulas, fostering a sense of gratitude and obedience. The implementation of Islamic values ​​that are rahmatan lil 'alamin (blessing for all nature) in mathematics learning, especially to form honest and fair characters in students.

This study examines adolescents' perceptions of the representation of premarital pregnancy in the film Dua Garis Biru (Two Blue Lines), and its impact on their views on relationships, responsibility, and moral values. Film is positioned as a mass communication medium capable of shaping public opinion and effectively conveying social messages, particularly to adolescents. The approach used was a qualitative reception study method, involving eight adolescent informants as the main participants. Data collection techniques were conducted through in-depth interviews, then analyzed using thematic coding using NVivo software, to identify patterns of perception and meaning that emerged from participant responses. The results showed that most adolescents viewed Dua Garis Biru as an educational film that portrayed the realities of adolescent life honestly and touchingly. The film was deemed successful in conveying messages about the importance of responsibility, self-control, and awareness of the consequences of premarital relationships. Furthermore, an understanding of the need for open sexual education and healthy communication between children and parents emerged. The adolescents also highlighted the representation of gender inequality and the greater social pressures felt by women in situations of premarital pregnancy. The film was considered not only entertainment, but also a learning medium capable of shaping adolescents' emotional, moral, and social awareness. The film's reflective and contextual storytelling encourages young audiences to better understand the social realities around them. Thus, Dua Garis Biru (Two Blue Lines) makes a significant contribution in conveying social and moral educational values to adolescents.  

This study compares the performance of two deep learning models, namely Convolutional Long Short-Term Memory (ConvLSTM) and Long-term Recurrent Convolutional Network (LRCN), in the task of recognizing human activity from videos. Human activity recognition is an important field in computer vision with many applications, such as security monitoring, human-computer interaction, and social media-based video analysis. ConvLSTM is a model that combines convolution operations with long-term memory LSTM, thus capable of capturing spatial and temporal information simultaneously. This approach is ideal for processing video data sequences that have spatial and temporal dimensions. On the other hand, LRCN combines the power of spatial feature extraction from Convolutional Neural Network (CNN) and temporal sequence modeling through Recurrent Neural Network (RNN), specifically LSTM, to understand movement patterns in videos. The study used the UCF50 dataset consisting of 50 activity classes, but was limited to five classes for the focus of the experiment. The dataset was divided into 80% for training and 20% for testing, and the model was drilled for 50 epochs using early stopping to prevent overfitting. The results show that both models have high training performance. ConvLSTM achieved a training accuracy of around 98% and a validation accuracy of 90%, while LRCN achieved a training accuracy of 99.5% and a validation accuracy of 88%. Although ConvLSTM demonstrated good stability on the validation data, further testing using TikTok videos as real-world data showed that LRCN had a higher confidence level in recognizing activities, with most predictions achieving confidence scores above 80%. This difference in performance indicates that while ConvLSTM excels in generalizing on training data, LRCN is more robust to real-world data variations.

The purpose of this study is to determine the pattern of the concept of integration between Science and Islam, to explore how this integration is implemented, and to identify the factors that influence its effectiveness in the context of learning for the Integrated Madrasah Science Competition (KSM) in Biology at MAN 1 Wonosobo. This study employs a qualitative research method, utilizing field research and descriptive research approaches. The findings indicate that the pattern of integration between Science and Islam in biology learning is interconnective, blending both perspectives seamlessly. Supervisory teachers, who predominantly have a pure scientific background in biology, play an active role in discussions and studies. The use of biology textbooks as learning resources, which integrate both scientific and Islamic content, is maximized, allowing for in-depth discussions between teachers and students. Key factors influencing the effectiveness of the Biology KSM include the curriculum and learning materials that emphasize the integration of Science and Islam. The competencies of interdisciplinary teachers who understand and master the integration of both sciences are crucial for the success of the Biology KSM. Additionally, support from all components of the madrasah is essential for creating a motivating and guiding framework that encourages the integration process. These findings suggest that the combination of academic expertise in both science and Islam, along with strong institutional support, contributes significantly to the effectiveness of the Integrated Madrasah Science Competition and enhances the learning experience for students. This study provides insights into how the integration of Science and Islam can be effectively implemented in the educational context, specifically within biology education.

Character education in Indonesia is faced with various problems based on education only as a knowledge transfer activity, to overcome this, the Ministry of Education and Culture issued an independent curriculum to solve the problem. The purpose of this study is how the method applied by MI Sunan Kalijogo in habituating character education based on the Pancasila student profile. The method used in this research is descriptive qualitative, the data from this study were obtained from interviews, observation, documentation, and literature research which are then called primary and secondary data. Character education based on Pancasila learner profile applied by MI Sunan Kalijogo is congregational prayer activities, religious studies, and MTQ. The implication of this research is a form of strengthening P5 and reconstructing character education patterns for schools at the elementary school level that use an independent curriculum.

The transition of children from early childhood education to elementary school (SD) is a critical phase in their psychological and academic development. During this phase, children face significant challenges, including changes to a more structured learning environment and increasing academic demands. At SDN 055991 in Langkat Regency, this phenomenon is reflected in the difficulties experienced by some students, particularly with basic skills such as reading, writing, and arithmetic, as well as with socializing with peers. These difficulties can impact children's long-term academic and social development. This study aims to identify the key factors influencing children's learning readiness during this transition period, utilizing artificial intelligence (AI) technology. Specifically, this study uses Artificial Neural Networks (ANN) and Decision Trees as tools to analyze the data obtained. The use of this data-driven approach allows for a more in-depth analysis of the complex patterns and relationships between various variables that influence children's learning readiness, such as family factors, social environment, and students' basic skills. This study also references various previous studies demonstrating the effectiveness of backpropagation and Deep Learning algorithms in the context of education and student performance prediction. This approach is expected to provide more precise solutions for understanding children's learning readiness and provide a more accurate picture of the factors contributing to difficulties experienced by students in the transition to elementary school. The results of this study are expected to provide relevant recommendations for parents, educators, and education policymakers to support children's learning readiness and strengthen basic education policies that are adaptive to the needs of students in this digital era.

The rapid development of information technology has triggered significant changes in communication patterns, including in da'wah activities. Amidst digital dominance and the rapid flow of information, a da'wah approach relevant to the communication characteristics of Gen Z is crucial. Gen Z is known for its fast, interactive communication style and preference for digital media. Therefore, this community service program is designed to introduce da'wah as an effective two-way communication process in addressing these dynamics. The main objective of this program is to improve digital da'wah literacy and foster motivation and practical skills in creatively conveying Islamic messages through social media platforms. This community service activity is carried out through a series of activities, including outreach, interactive discussions, and practical simulations for creating digital da'wah content. The outreach is intended to provide a basic understanding of da'wah in a digital context. Interactive discussions allow participants to share views and understand how da'wah can be carried out effectively in cyberspace. Meanwhile, the da'wah content creation practice provides participants with the opportunity to directly engage in creating da'wah messages that can be disseminated through social media. Evaluation of the activity is carried out through pre- and post-tests held before and after the program implementation. The analysis results showed an increase in participants' understanding of more than 35% across all tested indicators. The highest increase (56.3%) was recorded in their understanding of the importance of two-way communication in da'wah. Previously, many participants considered da'wah to be an activity limited to religious leaders. However, after participating in this program, they began to understand that da'wah is a task for every individual, and can be carried out through media closely related to their daily lives. Overall, this program succeeded in increasing knowledge, critical awareness, and enthusiasm for contextual da'wah among Gen Z.

The use of office stationery (ATK) plays a crucial role in supporting the smooth running of administrative activities within government agencies, particularly within the Financial and Development Supervisory Agency (BPKP). As an agency responsible for supervising and evaluating state financial management, the availability of adequate and timely ATK is a crucial supporting factor in ensuring the efficient and effective operation of BPKP. Unavailability of ATK can hamper administrative processes, while excess stock can lead to budget waste and inefficiency in logistics management. This study aims to implement an inventory control system for ATK use at BPKP using the Min-Max Stock method. This method is used to determine the ideal minimum and maximum limits for ATK inventory, with the aim of minimizing overstock and stockouts. With this approach, agencies can manage ATK procurement more efficiently based on actual needs and existing usage patterns. The results of the study indicate that the application of the Min-Max Stock method provides significant results in inventory management. For the type of ATK in the form of F4 size HVS paper, the minimum and maximum values are set at 12 reams. Meanwhile, for A4-sized HVS paper, the minimum quantity is 72 reams and the maximum is 98 reams. For other types of stationery, such as printer ink, the minimum and maximum quantities are set at 74 and 92 bottles, respectively. For BPKP logo folders, the recommended minimum is 240 sheets and the maximum is 325 sheets. By implementing this method, BPKP can optimally manage stationery inventory, thereby minimizing the risk of stockouts that could disrupt operations and preventing inefficient stockpiling. This approach contributes to more orderly, transparent, and cost-effective logistics governance within the government.

This study aims to analyze the correlation between learning models and student achievement at SMA Negeri 1 Kuala by applying the Apriori algorithm in data mining, using Rapid Miner software as the primary tool for analysis. The research is motivated by the shift in educational approaches from conventional teacher-centered methods toward more innovative strategies such as project-based learning and cooperative learning, which are expected to foster higher levels of student engagement and improve academic outcomes. In many schools, particularly at the secondary level, the choice of learning model, availability of facilities, and attendance rates are crucial factors that shape learning effectiveness and student performance. The data collected in this study include student grades, the types of learning models implemented, school facility conditions, and attendance rates for the 2023/2024 academic year, covering a total of 680 students. The Apriori algorithm was employed to discover hidden patterns and associations among these variables, enabling the identification of relationships between learning factors and academic achievement. By applying Rapid Miner software, the research systematically generated association rules that reflect meaningful correlations in the dataset. The results indicated that the use of the Indonesian language subject in combination with a cooperative learning model, adequate and complete school facilities, and good student attendance was strongly associated with the attainment of an A grade. This finding was supported by a support level of 53.33% and a confidence level of 100%, suggesting a robust and reliable relationship between these factors. The implementation of data mining techniques through Rapid Miner not only allowed for efficient data processing but also provided practical recommendations for educators and school administrators in designing effective instructional strategies.

Delivery delays pose a major challenge in the e-commerce industry, often leading to decreased customer satisfaction and negatively impacting business operations. In this study, the XGBoost (Extreme Gradient Boosting) algorithm is applied to predict delivery delays based on a dataset containing 96,476 records. These records include various features relevant to the delivery process, such as shipping distance, carrier performance, and order characteristics. The model achieves a high overall accuracy of 93.24%, indicating strong general performance. In particular, XGBoost demonstrates excellent results in predicting on-time deliveries, achieving a precision of 93% and a recall of 100%. However, the model struggles to correctly identify delayed deliveries. The recall for delayed deliveries is 0%, and the F1-score is extremely low at 0.01. This significant discrepancy reveals a critical limitation in the model's performance — the inability to detect minority class cases (delayed deliveries) due to class imbalance within the dataset. The results highlight the importance of addressing data imbalance in predictive modeling for delivery outcomes. When the dataset is dominated by on-time delivery records, the model tends to be biased toward that class, failing to learn the patterns associated with delays. To improve performance, the study recommends integrating class balancing techniques such as SMOTE (Synthetic Minority Oversampling Technique) to generate synthetic samples of the minority class. Additionally, the use of alternative evaluation metrics beyond accuracy — such as precision, recall, and F1-score for each class — is suggested to provide a more comprehensive understanding of model effectiveness. Overall, the study provides valuable insights into the complexities of predicting delivery delays and outlines practical strategies for enhancing future models in e-commerce logistics analytics.

This research aims to develop a recommendation system that can help retail business owners design more effective, data-driven promotional strategies. This system utilizes data mining techniques and the Apriori algorithm to extract association rules from consumer transaction data, thereby identifying more specific and accurate consumer purchasing patterns. Based on these patterns, the system can provide relevant promotional recommendations, such as product bundling, buy-one-get-one offers, or special discounts, which can attract consumer interest and increase sales. The system's implementation process is presented in the form of an interactive dashboard, which allows business owners to upload their transaction data, adjust analysis parameters, and visualize the promotional recommendation results in a way that is easier to understand and can be directly applied to their marketing strategies. This system not only provides well-structured promotional recommendations but also enables retail business owners to make more informed and efficient decisions in determining the type of promotion to implement, based on insights gained from analyzing their own transaction data. By utilizing this system, business owners can optimize their promotional strategies more efficiently and effectively, because they can quickly identify promotions that best suit consumer purchasing patterns. This can increase impulse sales, as relevant promotions will encourage consumers to purchase more products. Furthermore, this system shows great potential in increasing consumer engagement, as the promotions provided are more personalized and tailored to each consumer's preferences. Therefore, the implementation of this recommendation system has the potential to drive significant sales growth and help retail business owners achieve greater profits, as well as accelerate their business decision-making process. This system, ultimately, not only benefits business owners but also enhances the consumer shopping experience with promotions that are more tailored to their needs and preferences.

This study examines the role of Artificial Intelligence (AI) in piano education through a qualitative review of six recent academic sources. AI technology has brought about significant transformations in music learning methods, particularly for the piano instrument. Various AI applications such as automated performance feedback systems, musical accompaniment generators, technical error detection devices, and adaptive learning platforms have enabled new approaches to teaching and learning. AI provides instant feedback, tailored exercises to individual abilities, and creates more interactive and flexible learning environments. These innovations are considered to support the development of students' technical skills more effectively, while increasing learning motivation through personalization and ease of access. Furthermore, this study examines the information systems that support these AI applications, including human-computer interaction, audio signal processing, and the use of machine learning models to recognize playing patterns and technical errors. While AI offers significant benefits, concerns arise regarding its limitations in understanding and responding to the emotional aspects of music. AI is not yet capable of fully supporting the development of subjective and complex musical expression. Over-reliance on this technology is also feared to undermine students' critical thinking, artistic sensitivity, and creativity. Therefore, this study emphasizes the importance of a balanced integration between AI technology and human pedagogical roles, with the teacher remaining the primary facilitator in fostering expression, interpretation, and artistic values in piano learning. The study recommends further research on emotionally responsive AI, blended learning models, and long-term evaluation of AI's impact on students' artistic and musical development.  

The issue of determining the number of students' graduation times is one of the important indicators in transmitting the quality and effectiveness of the higher education process in universities. The rate of on-time graduation not only impacts accredited institutions, but also becomes a concern for campus management in designing learning strategies and academic guidance. This study aims to apply and compare two classification algorithms in data mining, namely C4.5 and K-Nearest Neighbor KNN, in predicting the accuracy of students' graduation times. Predictions are made based on academic attributes such as Grade Point Average GPA, number of credits that have been achieved, and Semester Grade Point Average IPS as input variables. The method used in this study is Knowledge Discovery in Database KDD which includes data selection, preprocessing, transformation, data mining, and evaluation of results. The study was conducted using the RapidMiner tool, with a dataset of 279 Informatics Study Program students from the 2015 to 2019 intake. The data was classified into two categories: "graduated on time" and "not graduated on time". The test results showed that the KNN algorithm provided better performance compared to C4.5. KNN produced an accuracy of 76.08%, with a precision of 73.11% and a recall of 41.92%. Meanwhile, the C4.5 algorithm produced an accuracy of 73.49%, with a precision of 64.62% and a recall of 41.89%. This difference in accuracy indicates that KNN is more effective in capturing patterns in the data and providing more accurate predictions in this context. Thus, the KNN algorithm can be considered a more optimal method to assist universities in predicting potential student admissions in a timely manner, thus enabling early intervention for students at risk of late graduation. This research also contributes to the development of data mining-based academic decision support systems in higher education.