Prediksi Status Kelulusan Mahasiswa Menggunakan Linear Discriminant Analysis dan Extreme Learning Machine

Abstract

Student graduation plays a crucial role in assessing the quality of higher education. Early prediction of student graduation can assist universities in taking appropriate and precise steps to improve student graduation rates. This study aimed to predict student graduation rates using a combination of Linear Discriminant Analysis (LDA) and Extreme Learning Machine (ELM) methods. The research steps included handling missing values to address incomplete data, Min–Max Scaler normalization to equalize the range of values in data attributes, dimensionality reduction using Linear Discriminant Analysis (LDA), and classification using Extreme Learning Machine (ELM). Model evaluation was conducted using K-Fold Cross Validation to obtain more objective results and reduce data distribution bias. Model performance was measured using accuracy, precision, recall, and F1-score. The test results showed that the best results were achieved with an accuracy of 91.34%, precision of 86.44%, recall of 79.05%, and F1-score of 79.33%. These results indicate that the combination of Linear Discriminant Analysis (LDA) and Extreme Learning Machine (ELM) is capable of producing good classification performance for predicting student graduation.