Application of Decison Tree Algorithm to Improve Student Learning Pattern Classification Model at Sempoa Sip Perjuangan

Abstract

This study aims to analyze the relationship patterns between attributes in the dataset using the Decision Tree model on the RapidMiner Studio platform. This model is used to identify various factors that affect the performance of participants in solving visual and auditory-based questions. The research stages include data preprocessing, model building, and performance evaluation based on accuracy, precision, and recall metrics. The results show that the Decision Tree is able to intuitively divide the data with attributes such as gender and test-taking method as the main factors. The final node of the decision tree provides a prediction of the number of questions that can be solved correctly. Model evaluation showed good accuracy, although there were indications of overfitting that required pruning. This research supports previous literature that highlights the influence of individual characteristics and learning methods on participant performance. The results can be used to design more personalized and effective learning strategies. Further studies are recommended to use larger datasets and other machine learning algorithms for comparison.