Concept

Prediction of Student Final Exam Performance in an Introductory Programming Course: Development and Validation of the Use of a Support Vector Machine-Regression Model

This study develops and validates a Support Vector Machine (SVM) regression model to predict final exam performance and identify at-risk students in an introductory programming course. Using data from 190 novice students on the ViLLE platform (2012-2016)—including homework assignments, demo exams, and prior programming knowledge—the model found these factors correlated with final grades. However, the SVM model achieved a low prediction accuracy of 52% overall and 46.4% for at-risk students, which the authors attributed to multicollinearity and the variables' inability to capture individual characteristics.

0

1

Updated 2026-07-02

Tags

Data Science