Publication Search

This study aims to analyze the factors that influence students' interest in continuing their education to college using a machine learning approach. Data was collected through an online questionnaire completed by 727 students between July 27 and August 22, 2025, covering 23 variables consisting of respondent identity (gender, grade level, major) as well as internal and external factors such as parental support, learning motivation, and preferred type of college. The data preparation stage was carried out through column cleaning, deletion of empty data, encoding of categorical variables, and division of the dataset into 80% training data and 20% test data. The Naive Bayes algorithm of the CategoricalNB type was used because it was suitable for the categorical nature of the data. The evaluation results showed that the model was able to predict student interest with 96% accuracy. For the class of students interested in continuing their studies, the precision, recall, and F1-score values were above 0.95, while the performance in the class of students who were not interested was slightly lower due to the smaller amount of data. These findings show that Naive Bayes is proven to be effective and reliable in classifying students' interest in continuing their studies and can be the basis for decision-making in designing more targeted educational strategies.

This study aims to investigate the factors influencing the continuance intention of Al-Kautsar Senior High School students in using metaverse-based learning media. The background of this research lies in the rapid adoption of immersive technologies in education, while students’ levels of acceptance have not yet been fully understood. The objective is to identify the antecedents of satisfaction, which subsequently influence continuous intention. The research model examines the effects of perceived interactivity, perceived sociability, perceived enjoyment, perceived ease of use, perceived security, and social influence on satisfaction. A quantitative approach was employed by distributing questionnaires to students, and the data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results indicate that satisfaction is a very strong and statistically significant predictor of continuous intention to use metaverse applications (β = 0.716, p < 0.001). The six hypothesized antecedent variables were not found to have a significant individual effect on satisfaction. In conclusion, for digital native students at Al-Kautsar Senior High School, factors such as ease of use, interactivity, and enjoyment have shifted from being drivers of satisfaction to becoming basic expectations (hygiene factors). Satisfaction itself emerges as the primary determinant, likely influenced by more substantive elements such as content quality or pedagogical design rather than merely the technical features of the platform.

This study aims to analyze and compare the performance of the Naive Bayes, K-Nearest Neighbors (KNN), and Decision Tree algorithms in predicting the purchase intention of e-commerce visitors using the Online Shoppers Purchasing Intention Dataset, which consists of 12,330 records and 18 variables, with the Revenue variable serving as the classification target. The preprocessing stage involved transforming categorical and boolean variables into numerical form, standardizing features using StandardScaler, and splitting the dataset into 80 percent training data and 20 percent testing data. Model evaluation was conducted using accuracy, precision, recall, F1-score, and ROC-AUC metrics, and was further strengthened by 10-fold cross-validation to obtain more stable results. The findings indicate that KNN achieved the highest accuracy of 0.866180, while Naive Bayes produced the highest recall value of 0.690998 and the highest ROC-AUC value of 0.821696. Meanwhile, Decision Tree demonstrated relatively balanced performance with an accuracy of 0.857259 and an F1-score of 0.571776, whereas the cross-validation results identified KNN as the model with the highest average accuracy of 0.8770. These findings suggest that the selection of a classification model for purchase intention prediction cannot rely solely on a single evaluation metric, as each algorithm possesses different strengths. Therefore, a comparative approach among algorithms can help determine the most suitable model for supporting consumer behavior analysis on e-commerce platforms.

Decision Support System couple the intellectual resource of individuals with the capabilities of the computer to improve the quality of decision. It's a computer based support system for management decision makers who deal with semi-structured problem. An integrated decision support system for use in an machine mollen product has been developed. It incorporates a linear Programming model that represents the contribution optimal and optimizes the production water pump and mollen machine. An optimization model is performed using a management scient model called linear programming approach in older to determine media selection. To use this model, the DSS needs ti interface with another software. Mathematical Programming is a technique used in mathematical models, particularly optimization models, to assist in decision making. The Simplex Method is "a systematic procedure for generating and testing candidate vertex solutions to a linear program." (Gill, Murray, and Wright, p. -137) It begins at an arbitrary corner of the solution set. At each iteration, the Simplex Method selects the variable that will produce the largest change towards the minimum (or maximum) solution. The  development of computer programs to be used as Decision Support Systems involves several tasks such as mathematical modeling, technical and data collection and development of a user friendly interface.

When creating databases for GIS-applications often existing maps are scanned and vectorised for used. However, vectorisation becomes obsolete when GIS-objects can be referred to both in theme and geometry in a raster environment. This article shows to use model spatial data raster and vector for GIS - applications in both the graphical and image structure. Geographical data must first be converted into a computer- readable format before it can be used in a GIS. Spatial data are "elements that can be stored in map form." These elements correspond to a uniquely defined location on the Earth's surface. Spatial data have also been describe as “any data concerning phenomenon a really distributed” in two or more dimensions. (Peuquet and Marble, I990.) Data model is the rules to convert real geographical variation into discrete objects. There are two main GIS data models - vector and raster. Each of the two data models has specific types of data, analysis and displays that can handle better than the other system. The vector model represents geographical reality as a series of discrete objects or features, classified as points, line's or areas (polygons). The geographical co-ordinates describing the locations of these features are stored in the computer database which lies at the heart of the GIS. In the raster model a regular grid of cells, or pixels, is used to encode the features found on the earth's surface. Each pixel has a number associated with it representing; the value of a geographical phenomenon, such as terrain elevation, soil type or biomass. Layers of raster grids covering the same region can be built up to represent further variables.