Journal of Big Data (May 2025)

Student academic performance prediction via hypergraph and TabNet

  • Yisheng Yang,
  • Shiyu Zhao,
  • Sufang An,
  • Xiaoyong Li,
  • Yong Zhang

DOI
https://doi.org/10.1186/s40537-025-01170-1
Journal volume & issue
Vol. 12, no. 1
pp. 1 – 24

Abstract

Read online

Abstract Student academic performance prediction plays a very important role in student management. With the development of deep learning, there has been some related research work on predicting student academic performance. Although many factors influence students’ academic performance, students at the same university tend to have similar intellectual levels and learning environments. Therefore, learning behaviors can significantly impact their academic performance. Thus, modeling students’ behavior can enable the prediction of their academic performance. However, existing methods mostly focus on modeling individual student behaviors, neglecting the complex associations among students hidden within campus behavioral data. In reality, the associations between students often involve higher-order, multi-to-multi relationships, rather than simple, pairwise connections. At the same time, most data-driven deep learning models are not interpretable. But in fact, the analysis of behaviors that affect student academic performance is more useful in many cases. To address these issues, this paper proposes a student academic performance prediction model that combines hypergraphs and TabNet. This method first processes and extracts usable behavior features from collected multi-source campus behavior data; secondly, it utilizes K-Nearest Neighbors (KNN) to construct a hypergraph to describe the higher-order associations among students; then, it uses hypergraph convolution to aggregate neighborhood features to learn sample embedding representations; finally, the academic performance of students are predicted by the TabNet model. Experimental results on real student behavior datasets indicate that the precision, recall, and F1 score of the method proposed in this paper are improved compared to baseline methods. Additionally, using hypergraphs and TabNet can help to explain the relationship between student behavior and performance at the feature level.

Keywords