Predicting Senior High School Students' Higher Education Intention using Naive Bayes Algorithm: A Case Study in SMAN 6 Luwu Timur, Indonesia

Abstract

Students' interest in continuing their education to a higher level is an essential indicator of improving the quality of human resources. However, the factors influencing this interest are diverse, encompassing academic, social, and economic aspects. This study aims to predict the interest of students at SMAN 12 Luwu Timur in continuing their studies at university using the Naive Bayes algorithm. Data were collected through questionnaires administered to students, covering attributes such as tuition fees, parental income, college location, motivation, environmental support, and the 94 12th-grade s' desire to continue. The analysis process included data cleaning, transformation of categorical variables, and dividing the data into training and test data. The Naive Bayes algorithm was used to classify students into two categories: "interested in continuing" and "not interested in continuing." The results showed that the model had an accuracy of 84.21%, indicating quite good performance for categorical education data. Parental income and motivation proved to be the most influential factors influencing interest in continuing studies. These results suggest that the Naive Bayes algorithm can be an effective predictive tool for early identification and educational strategy design, encouraging students to progress to higher levels.