Towards efficient student performance prediction with TabPFN: A few-shot learning approach in data-scarce scenarios
Abstract
Accurate prediction of student academic performance is crucial for enhancing educational outcomes and enabling personalized learning interventions. However, the limited availability of labeled data in many practical educational settings poses significant challenges for conventional machine learning models, which often require large datasets to achieve satisfactory performance and are prone to overfitting. To address this issue, we propose a novel few-shot learning framework based on the Tabular Prior-Data Fitted Network (TabPFN). By integrating a Transformer-based architecture with Bayesian inference, TabPFN effectively leverages meta-learned priors to perform high-quality predictions without task-specific finetuning. We evaluate our approach on two public educational datasets, Mathematics and Portuguese student performance, under small sample conditions. Experimental results demonstrate that TabPFN outperforms a range of traditional and deep learning benchmarks, achieving accuracies of 92.36% and 95.49%, respectively. Additionally, we employ SHAP (Shapley Additive Explanations) to interpret model decisions, identifying key influencing factors such as prior grades (G1, G2) and prior educational experience. The findings indicate that TabPFN constitutes a promising and effective solution for educational prediction in data-scarce scenarios but also provides actionable insights for instructional design and student support.