<![CDATA[This study analyzes how Naive Bayes and K-Nearest Neighbor (KNN) predict learning outcomes based on artificial intelligence (AI). The main focus of this study is the difficulty of algorithms in handling complex learning data and the contribution of Association Rule Mining (ARM) attribute features in improving prediction accuracy. The methods applied include two classification algorithms (KNN and Naive Bayes) in an exploratory-comparative quantitative research design, as well as the application of ARM to uncover hidden patterns among variables using the apriori algorithm. Data for 368 students with prior experience in artificial intelligence technology was collected through an online survey. Although KNN outperforms in recall, the study results show that Naive Bayes has higher precision. By detecting hidden correlation patterns that cannot be identified by conventional classification methods, ARM improves classification results. The discussion emphasizes that the selection of the best algorithm depends on the application's objectives, namely whether the priority is on classification accuracy or the range of relevant results. Based on these findings, a hybrid technique combining KNN, Naive Bayes, and ARM is highly recommended for creating a more efficient and accurate prediction system to support AI-based education.]]>
Copyrights © 2025
