Menggunakan Metode Machine Learning Untuk Memprediksi Nilai Mahasiswa Dengan Model Prediksi Multiclass

This study aims to predict students' final GPA and study duration using machine learning methods. The model applied in this study is the Random Forest Regressor, which was trained using a dataset that includes various factors such as semester GPA, socio-economic background, demographics, learning activities, and the difficulty level of courses. The results of the study show that the model produces less accurate predictions, with a Mean Squared Error (MSE) of 0.34 for the final GPA and 3.83 for the study duration. Furthermore, the R² Score for the predictions of final GPA and study duration are -0.079 and -0.055, respectively, indicating that the model's prediction performance is not optimal. In the multiclass classification section, the model is able to classify students into several categories based on their final GPA, such as Cum Laude, Very Satisfactory, Satisfactory, and Fair. From the testing results, the model predicts a final GPA of 2.92 for a new student example, which is classified into the "Satisfactory" category, with a predicted study duration of 8 semesters. The conclusion of this study indicates that the regression model used requires improvement to achieve better accuracy. Other factors, such as feature optimization or the use of alternative algorithms, can be explored in future research to enhance the prediction results.