Data mining helps provide precise and careful decisions. Student graduation on time is one of the assessment points in the higher education accreditation process. However, student graduation cannot always be detected quickly, which can reduce the assessment of a university in the accreditation process. This problem arises to find out whether students will be able to graduate on time or not Classification method for predicting student graduates using the Naïve Bayes algorithm. Whether a student graduates on time or not, it is hoped that the results will provide information and input for the university in making future policies. From the results of this test, it was found that by applying the Naïve Bayes algorithm the system can predict student graduation in a timely manner. After comparing several literatures, it can be concluded that this method can be used for this prediction with an accuracy rate of 90%. This literature review is important as a supporting factor for research.

Grouping student learning outcomes is a strategic step to improve the quality of learning by understanding student achievement patterns in more depth. This study aims to analyze student learning outcomes at SDN 3 Ardirejo by applying the K-Means clustering method, which is designed to group data based on similarities in academic value characteristics from various subjects during one semester. The clustering results show the effectiveness of this algorithm in dividing students into high, medium, and low achievement clusters, making it easier for teachers to design adaptive learning strategies that suit the needs of each group. In addition, the information generated provides valuable insights for planning intervention programs, such as remedial learning for low-achieving students or enrichment materials for high-achieving students. This study contributes to a more systematic management of educational data at the elementary school level and is expected to be a reference for more effective decision-making, both at the school level and by educational stakeholders.

In the competitive world of business, identifying high-risk customers is critical to minimizing churn rates and increasing profitability. This research uses data mining techniques using the C4.5 decision tree algorithm to classify customers based on their churn risk. The research stages include data collection, cleaning, data processing, as well as dividing the data into training and testing sets. The implementation of this algorithm was carried out using RapidMiner software, which facilitates customer clustering and predicting behavior based on historical attributes. The evaluation results show the model has an accuracy of 74.59%, with precision and recall indicating the model's ability to identify high-risk customers. Thus, the Decision Tree C4.5 algorithm is proven to be effective in supporting decision making for customer churn risk mitigation strategies.

Sleep disorders, including insomnia, can be influenced by various lifestyle factors, such as sleep duration, sleep quality, physical activity, and individual health conditions. This study aims to categorize the risk level of insomnia based on lifestyle using the K-Means clustering algorithm. The data used include sleep duration, sleep quality, heart rate, and daily step count. Through the implementation of the K-Means algorithm, the data is analyzed to group individuals into several categories based on existing lifestyle patterns. The results of the study show a correlation between a healthy lifestyle and better sleep quality. In addition, the resulting clusters provide insight into lifestyle characteristics that affect the risk of insomnia, so that they can be the basis for recommendations for more targeted health interventions. This study is expected to contribute to the development of data-based sleep disorder management strategies by utilizing machine learning methods, especially the K-Means algorithm, to support efforts to improve the quality of life of the community.

The research aims to explore and understand energy consumption patterns in households. By using the Decision Tree algorithm, to classify the level of electrical energy consumption. And data on household electrical energy consumption can be obtained from various sources, such as Household electricity meter. Survey or questionnaire filled out by homeowners regarding the use of electrical appliances. Based on the image above, the application of the Decision Tree algorithm in analyzing risk factors for  The classification of household electrical energy consumption produces an accuracy value of 100.00%. From the displayed confusion matrix, we can see the distribution of predicted and actual values for various classes. For example, in the class "true 110 25," there are 17052 correct predictions. The evaluation results also show the precision and recall values for each class. The highest precision was achieved in the "true 2205" class with 100% recall, while the precision was found in the "true 122.5" class of 100.00%.

Kemiskinan merupakan salah satu masalah sosial yang terus menjadi tantangan bagi pemerintah di berbagai negara, termasuk Indonesia. Dalam upaya mengidentifikasi faktor-faktor yang memengaruhi tingkat kemiskinan, analisis data yang tepat diperlukan untuk mendukung pengambilan kebijakan yang efektif. Penelitian ini bertujuan untuk mengklasifikasikan tingkat kemiskinan di Indonesia dengan menggunakan algoritma Decision Tree, salah satu metode pembelajaran mesin yang populer. Data yang digunakan dalam penelitian ini mencakup indikator ekonomi, demografi, dan sosial yang relevan dengan kemiskinan di Indonesia. Dengan menggunakan algoritma Decision Tree, kami dapat mengidentifikasi variabel-variabel kunci yang berperan dalam klasifikasi tingkat kemiskinan serta membangun model prediksi yang dapat membantu dalam pengambilan keputusan. Hasil penelitian menunjukkan bahwa algoritma Decision Tree memiliki kinerja yang baik dalam mengklasifikasikan data kemiskinan dan memberikan wawasan mendalam tentang faktor-faktor yang memengaruhi kemiskinan di Indonesia. Temuan ini diharapkan dapat berkontribusi dalam upaya penanggulangan kemiskinan melalui pendekatan berbasis data.

Data mining, or data mining is the process of collecting and processing data to extract important information. The stages in the data mining process are useful for finding a particular pattern from a large amount of assessment data. This goal is to find out and form student data clusters based on grades so that they become a cluster, so that the results of student clusters can be a reference in improving student grades in the next learning process. The results of the evaluation and assessment of students are carried out by teaching staff or teachers in conducting assessments during the learning process. In the learning process there are 2 assessment categories, namely UTS and UAS student grades. The results of grouping student grade data using the K-Means clustering method show that based on the results of student data clusters in one semester, cluster 0 is obtained with 7 students, cluster 1 is 3. The results of testing using rapid miner show that there are 7 students who have grades with a good average and there are 3 students with a poor average grade.

Student attendance in lectures plays a crucial role in academic achievement and the quality of learning. The Decision Tree algorithm is used to analyze student attendance patterns with a dataset containing 6,607 entries from Kaggle, comprising 20 related attributes. Using RapidMiner, the analysis process includes data splitting, model building, and performance evaluation. The model achieved 49.96% accuracy, with the best performance in the "Medium" class (50.40% precision, 98.12% recall) but showed weaknesses in the "High" and "Low" classes. These results highlight the importance of data-driven approaches to designing effective strategies, such as rescheduling or improving teaching methods, to enhance student participation.

Determining classes for outstanding students based on exam results is a crucial step in promoting the improvement of learning quality. This study applied a data mining method using the K-Means Clustering algorithm to group students based on their exam results. The process includes collecting exam score data, preprocessing the data, and applying the K-Means algorithm to form several student groups based on their achievement levels. Through this algorithm, students are clustered into groups with similar characteristics, such as excellent, average, and those requiring more attention. The study's results indicate that the K-Means Clustering approach can provide an accurate representation of the distribution of student abilities, serving as a basis for designing more effective and equitable learning strategies. This implementation is expected to help schools identify students' potential more objectively and enhance overall educational quality.

Implementation of the Naive Bayes algorithm for the classification of recipients of the Certificate of Inability to Pay (SKTM) assistance in Pesanggrahan Village. The classification process is carried out manually and using the RapidMiner application to validate the results. Manual calculations are carried out by calculating the probability of each attribute, such as occupation, age, income, marital status, vehicle, and asset ownership. The calculation results show that the probability for the "eligible" category is 0.097254, while the "uneligible" category has a probability of zero, so that the resident is classified as eligible to receive assistance. And, the calculation results using RapidMiner show results that are consistent with manual calculations. The Naive Bayes algorithm successfully classifies data with high accuracy, ensuring that assistance is more targeted to residents who meet the criteria. The implementation of this method provides an effective solution to overcome the problem of inaccurate distribution of assistance, increasing efficiency and transparency in decision-making by village officials. Thus, the Naive Bayes algorithm can be used as a tool in the process of determining recipients of assistance that is more objective and data-based.