Deep Learning-Based Student Grade Prediction and Interpretability Analysis

DOI

10.2991/978-94-6239-691-3_20How to use a DOI?

Keywords

Deep learning; Student grade prediction; Interpretability analysis; Pedagogical suggestions

Abstract

Addressing the limited accuracy of traditional machine learning methods in handling complex nonlinear features, as well as the challenges of applying deep learning models to pedagogical practice due to their inherent lack of interpretability, this study proposes a student grade prediction framework that integrates Gated Recurrent Units (GRUs) with SHAP interpretability analysis. Using an educational dataset from Kaggle, an end-to-end prediction model was constructed, selecting study duration, sleep duration, attendance rate, and previous academic performance as input features. Experimental results demonstrate that the GRU model achieves a Root Mean Square Error of 3.0884 in grade prediction, significantly outperforming baseline models such as Support Vector Machine and Random Forest. Furthermore, SHAP analysis elucidates the coupling effects of these four features on academic performance, providing an empirical basis for data-driven precision instruction.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Youhui Yu
PY  - 2026
DA  - 2026/05/31
TI  - Deep Learning-Based Student Grade Prediction and Interpretability Analysis
BT  - Proceedings of the 2026 5th International Conference on Educational Innovation and Multimedia Technology (EIMT 2026)
PB  - Atlantis Press
SP  - 190
EP  - 198
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6239-691-3_20
DO  - 10.2991/978-94-6239-691-3_20
ID  - Yu2026
ER  -