Memprediksi Kinerja Akademik Mahasiswa menggunakan XGBoost

Predicting the academic performance of students involves comprehending, analyzing, and forecasting the diverse factors that can impact their achievements. One of the key objectives of this study is to enhance our understanding of the current academic performance of students, utilizing data sourced from a predefined objective—specifically, the grades received in the final semester exams, which were extracted from a Kaggle dataset. Various methods can be utilized for predicting student performance, and among the well-regarded approaches is regression. The employed technique is Extreme Gradient Boosting, commonly referred to as XGBoost. The outcomes derived from the XGBRegressor method reveal an MSE of 0.036, RMSE of 0.192, and MAE of 0.148. These outcomes signify that the model provides precise predictions with minimal errors, as lower error values are indicative of accurate predictions.