Kanformer: an attention-enhanced deep learning model for predicting student performance in virtual learning environments

With the rapid growth of digital education, massive open online courses (MOOCs) have gained widespread popularity. However, high failure rates and low completion rates remain challenges, highlighting the need for accurate student performance prediction to identify at-risk students and implement timely interventions. Many existing models assume simplistic or linear dependencies, failing to capture the complex relationships and cross-dimensional interactions between different student features. Therefore, KANFormer model is developed, a novel deep learning (DL) architecture that integrates multi-head self attention (MHSA) mechanisms with Kolmogorov–Arnold networks (KAN) to effectively captures complex patterns within large-scale student datasets, enabling more accurate predictions of student performance. KANFormer processes student demographic, academic, and engagement features from the open university learning analytics dataset (OULAD) while applying a feature elimination process to enhance dataset quality, reduce redundancy, and mitigate multicollinearity, ensuring optimal predictive performance. The model is evaluated on both binary and multi-class classification tasks, distinguishing successful students (“Distinction” & “Pass”) from unsuccessful ones (“Fail” & “Withdrawn”), while also predicting individual performance categories. Ablation experiments analyze the impact of MHSA and KAN on model performance. Experimental results on the OULA dataset, comprising over 29,000 samples, demonstrate that KANFormer outperforms traditional and state-of-the-art models, achieving superior accuracy, precision, and F1-score in student performance prediction. To enhance interpretability, SHAP (SHapley Additive exPlanations) values are utilized to quantify each feature’s contribution to predictions. SHAP analysis shows that academic assessments (exam scores, TMAs, CMAs) are the most influential predictors of student success, while engagement indicators play a secondary role. Furthermore, the model’s generalization ability is validated on additional datasets, including ASSISTments2012, xAPI, and the Mathematics and Portuguese Language Courses dataset, proving its scalability and robustness across different educational contexts. By accurately identifying at-risk students, KANFormer offers a scalable, interpretable, and highly effective solution for improving student retention and success in online education, providing actionable insights for personalized learning interventions.