Application of Decision Tree Algorithm for Classifying Low Student Academic Performance

Abstract

This study aims to develop a student graduation classification model using the Decision Tree algorithm based on three main variables: attendance, exam scores, and assignment completion status. Data were collected through literature review, observation, and interviews. The preprocessing stage involved data cleaning and transformation to make it suitable for algorithmic processing. The model was trained and tested using 20% of the dataset. Evaluation results show that the model achieved 100% accuracy, precision, recall, and F1-score, with no classification errors. Decision tree analysis revealed that attendance was the most dominant variable in determining graduation, followed by assignment completion and exam scores. Despite the excellent performance, the limited dataset highlights the need for further studies using larger datasets and cross-validation to enhance model generalization. This model has the potential to serve as an objective decision-support tool for teachers in early identification of students at risk of not graduating.