Analisis Runtun Waktu Untuk Memprediksi Jumlah Mahasiswa Baru Dengan Model Random Forest

Abstract

Admission of new students is an important process in educational institutions such as tertiary institutions which is useful for screening accepted prospective students according to the criteria determined by the college. The purpose of this study is to predict the number of new students using the Random Forest model with the new student admissions dataset of XYZ University. The Random Forest Model is a machine learning algorithm that is excellent at solving classification and regression problems. Based on the research results, it was found that the resulting model has an accuracy rate of 99.8% with MSE and MAE values of 0.02% in predicting new students. The best parameter of the model with a maxnodes value of 100 and ntree 900 and a decreasing trend in the number of students for the next few years.