Prediksi Tingkat Adaptasi Pelajar dalam Pendidikan Online menggunakan Support Vector Machines dengan Optimasi GridSearch CV

Online education has become part of the learning method in most educational institutions in various countries. Starting from Elementary School, Middle School to College and University. It also took significant time to develop to optimize online education. An educational institution needs to be informed about the effectiveness of online education so that in the future they can determine what steps to take for more optimal online education for students. Our main motivation is to contribute to this problem, by analyzing factors closely related to online education. In this study, we used datasets from Kaggle by applying the Support Vector Machine (SVM) algorithm method with hyperparameter-tuning GridSearchCV optimization. Kernel Polynomial is the best parameter recommendation from this study's GridSearchCV optimization technique. Accuracy before optimization is 80%, while after optimization is 95%. The application of the SVM method with optimizing the hyperparameter-tuning GridSearchCV allows us to obtain higher accuracy results or an increase of 14%.