<![CDATA[This study aims to analyze the application of data mining using the Naive Bayes algorithm to predict the impact of economic factors on elementary school students living in plantation areas. The dataset used in this research consists of student records obtained from SDN 113820 Perkebunan Berangir, including variables such as distance from home to school, student age, early childhood education background, ownership of the Kartu Indonesia Pintar (KIP), and parental income. A total of 95 records were utilized as training data and processed using Orange software version 3.39.0. The evaluation results indicate that the Naive Bayes model achieved an accuracy of 85.3% with an Area Under Curve (AUC) value of 1.000 for both classes, demonstrating excellent classification capability. Although some misclassification occurred in the non-eligible class, the overall performance confirms that Naive Bayes is an effective and reliable classification method for analyzing socioeconomic factors in educational contexts. The findings suggest that this approach can support data-driven decision-making in educational assistance programs.]]>
Copyrights © 2026
