2026-10-07T09:47:01Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33988137 2026-09-24T17:33:27Z category_734 category_931 category_106 portal_5 item_type_3 month_year_09_2026

<p>The performance comparison results of each model.</p> Qiang Yin (600539) Biological Sciences not elsewhere classified Information Systems not elsewhere classified Science Policy traditional models attained shapley additive explanations publicly available dataset providing technical support predicting student achievement outperforming traditional models data fitted network predicting academic performance achieving performance comparable improving educational outcomes existing predictive models additional case study exhibiting stronger robustness div >< p 2 </ sup shap analysis reveals suboptimal performance study introduces existing algorithms educational domain “ black sized datasets significant importance secondary education sample sizes results demonstrate personalized instruction model ’ learning behavior future research fold cross employed 10 dual challenges decisive role attendance rate 500 samples 4000 ), <div><p>Predicting student academic performance is of significant importance for enabling timely educational interventions and improving educational outcomes in secondary education. However, existing predictive models in educational data mining often face the dual challenges of limited interpretability and suboptimal performance on small to medium-sized datasets. This study introduces the Prior-Data Fitted Network (TabPFN) combined with SHapley Additive exPlanations (SHAP) to construct an interpretable machine learning framework for predicting student achievement. Utilizing a publicly available dataset of 4,000 Spanish high school students (SAP-4000), we employed 10-fold cross-validation to train and compare eight machine learning models. The results demonstrate that TabPFN achieves superior predictive performance, with an RMSE of 4.8454, an R² of 0.9216, and an MAE of 3.7950, outperforming traditional models. Comparative analyses across varying data scales indicate that TabPFN maintains high accuracy even when sample sizes are reduced to 500 samples, achieving performance comparable to or better than what traditional models attained at 3,500 samples, exhibiting stronger robustness than commonly used ensemble learning methods such as XGBoost. SHAP analysis reveals that learning behavior and study habit features—specifically weekly study hours, attendance rate, and tutoring status—play a decisive role in predicting academic performance. The proposed framework combines strong predictive performance with interpretability, overcoming the “black-box” limitation prevalent in existing algorithms. It is well-suited for small to medium-scale data modeling tasks in the educational domain, providing technical support for personalized instruction and intervention, while also offering methodological references for future research. An additional case study on a distinct student performance dataset further confirms the model’s robustness and generalizability across different educational prediction tasks.</p></div> 2026-09-24T17:33:12Z Dataset Dataset 10.1371/journal.pone.0328634.t003 https://figshare.com/articles/dataset/_p_The_performance_comparison_results_of_each_model_p_/33988137 CC BY 4.0