Penerapan Model Support Vector Machine dalam Prediksi Keberhasilan Belajar Pemrograman

Application of Support Vector Machine Model in Predicting Programming Learning Success

Abstract

Programming learning success is an important indicator in information technology education; many students still struggle to understand algorithmic concepts, logic, and code implementation. This problem indicates that a data-driven approach is needed to identify students' initial successes and failures in programming learning. The purpose of this study is to develop and validate a predictive model for programming learning success using Support Vector Machine (SVM), a classification algorithm. This research method includes steps such as data collection and preprocessing, feature selection, splitting the dataset into training and test sets, training the SVM model with parameter optimization, and evaluating performance using the test set. The results show that the SVM model achieves good classification performance with an accuracy of 87.5%, precision of 85.7%, F1 score of 87.8%, and AUC of 0.91, placing it in the excellent category. These findings indicate that the model has strong discriminatory power in distinguishing between successful and unsuccessful students. Therefore, the SVM method has been proven effective as a data-driven prediction system. This also allows for the development of more targeted and adaptive learning intervention strategies and academic decision-making.