Klasifikasi Pemilihan Jurusan Sekolah Menengah Kejuruan Menggunakan Gradient Boosting Classifier

Abstract

The selection of the majors remains a crucial factor for prospective students who will pursue their education at SMK. However, students tend to follow the choices of their parents or friends. They are not considering the curriculum according to their interests and abilities. As a result, many students have difficulties following the lesson, and their academic achievement decreases. The RIASEC model is one of the interest detection methods used to determine the student's personality type. This study aims to develop a model to predict the choice of majors at SMK Yadika 12 Depok. We compared five classifiers on the major's selection data sets at vocational schools. In addition, we performed hyperparameter tuning using GridsearchCV to obtain the most influential parameters from the selected classification algorithm. The algorithms implemented are Multinomial Naive Bayes, Gaussian Naive Bayes, Bernoulli Naive Bayes, Gradient Boosting Classifier, Decision Tree Classifier, K Neighbors Classifier, and Logistic Regression. The test results show that the Gradient Boosting Classifier with Hyperparameter Tuning using GridSearchCV maintains an accuracy of 72% and class recall reaches 76%.