Pengembangan Model Kecerdasan Mesin Extreme Gradient Boosting Untuk Prediksi Keberhasilan Studi Mahasiswa

Abstract

The purpose of this study is to investigate the application of the Extreme Gradient Boosting (XGBOOST) model in machine learning for a dataset on student academic achievement. The research employs a quantitative approach, utilizing student retention data and conducting data processing in Jupyter Notebook. The primary outcome of this study is the performance evaluation of the Extreme Gradient Boosting machine learning model. The significance of this research lies in the development of a machine learning model that can aid higher education institutions in forecasting student academic success. The key discoveries of this study encompass predictive factors associated with student academic achievement. The Extreme Gradient Boosting model has demonstrated its effectiveness in predicting the student academic success dataset with an accuracy rate of 76.8%.