Improvement of Applicability in Student Performance Prediction Based on Transfer Learning

TL;DR

This paper introduces a transfer learning approach using neural networks to improve student performance prediction across different datasets, demonstrating enhanced accuracy and generalization, especially with limited data.

Contribution

It presents a novel transfer learning method with layer freezing strategies to boost prediction accuracy in student performance models across varying data distributions.

Findings

Freezing more layers improves performance on complex, noisy data.

Fewer frozen layers are better for simpler, larger datasets.

Transfer learning reduces errors and enhances model generalization.

Abstract

Predicting student performance under varying data distributions is a challenging task. This study proposes a method to improve prediction accuracy by employing transfer learning techniques on the dataset with varying distributions. Using datasets from mathematics and Portuguese language courses, the model was trained and evaluated to enhance its generalization ability and prediction accuracy. The datasets used in this study were sourced from Kaggle, comprising a variety of attributes such as demographic details, social factors, and academic performance. The methodology involves using an Artificial Neural Network (ANN) combined with transfer learning, where some layer weights were progressively frozen, and the remaining layers were fine-tuned. Experimental results demonstrated that this approach excels in reducing Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), while improving the coefficient of determination (R2). The model was initially trained on a subset with a larger sample size and subsequently fine-tuned on another subset. This method effectively facilitated knowledge transfer, enhancing model performance on tasks with limited data. The results demonstrate that freezing more layers improves performance for complex and noisy data, whereas freezing fewer layers is more effective for simpler and larger datasets. This study highlights the potential of transfer learning in predicting student performance and suggests future research to explore domain adaptation techniques for unlabeled datasets.