Implementasi Extra Trees Classifier dengan Optimasi Grid Search CV pada Prediksi Tingkat Adaptasi

Innovations and advancements in technology are always happening, especially in the fields of communication technology, education technology, and information technology. Educational technology, in particular, is experiencing rapid development with the popularity of online education in many educational institutions. Therefore, understanding the extent to which learners can adapt to the online education environment is important. Predicting learners' adaptation level is key for educators and online learning system developers to improve the effectiveness and quality of the learning experience. This research uses datasets from Kaggle and applies the Extra Trees Classifier algorithm method with Hyperparameter Tuning Grid Search CV optimization. Before optimization, the accuracy of the results reached 95.85%, and after optimization, the accuracy increased to 96.26%. The implementation of the Extra Trees Classifier method with Hyperparameter Tuning Grid Search CV optimization managed to increase accuracy by 0.41%. These results show that the implementation of the Extra Trees Classifier method with Hyperparameter Tuning Grid Search CV optimization provides better results compared to the use of algorithms without optimization.