ClickTree: A Tree-based Method for Predicting Math Students' Performance Based on Clickstream Data

The prediction of student performance and the analysis of students’ learning behaviour play an importantrole in enhancing online courses. By analysing a massive amount of clickstream data that capturesstudent behaviour, educators can gain valuable insights into the factors that influence students’ academicoutcomes and identify areas of improvement in courses. In this study, we developed ClickTree, a treebasedmethodology, to predict student performance in mathematical problems in end-unit assignmentsbased on students’ clickstream data. Utilising extensive clickstream data, we extracted a novel set offeatures at three levels, including problem-level, assignment-level and student-level, and we trained aCatBoost tree to predict whether a student will successfully answer a problem in an end-unit assignmentor not. The developed method achieved an Area under the ROC Curve (AUC) of approximately 79%in the Educational Data Mining Cup 2023 and ranked second in the competition. Our results indicatethat students who performed well in end-unit assignment problems engaged more with in-unit assignmentsand answered more problems correctly, while those who struggled had higher tutoring requestrates. We also found that students face more difficulties with “check all that apply” types of problems.Moreover, Algebra II was the most difficult subject for students. The proposed method can be utilisedto improve students’ learning experiences, and the insights from this study can be integrated into mathematicscourses to enhance students’ learning outcomes. The code and implementation is available athttps://www.kaggle.com/code/nargesrohani/clicktree/notebook.