| Summary: | The increasing popularity of educational programs by Chinese and foreign partners in China's universities presents challenges in administration due to differences in organization, social expectations, and academic requirements. This study presents a prediction model using Machine Learning techniques to assess student satisfaction levels. The Gradient Boosting Machine (GBM) framework, enabled by Principal Component Analysis (PCA), was used to collect data from 1,237 students. The approach was compared to other ML models like Random Forest, Linear Regression, Naïve Bayes, and Support Vector Machine and trained and validated using 5-fold cross-validation. The PCA+GBM model scored most effectively of significant metrics, with 93% accuracy, 92% precision, 91% recall, and 91.5% F1-score. Policymakers and educational administrators can use the outcomes as an incentive to enhance the strategy and standard of Higher Education (HE) that are run in collaboration between China and foreign countries. © 2024, Transnational Press London Ltd. All rights reserved.
|
|---|