{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:09:14Z","timestamp":1790273354803,"version":"4.1.0"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    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 R\n                    <jats:sup>2<\/jats:sup>\n                    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\u2014specifically weekly study hours, attendance rate, and tutoring status\u2014play a decisive role in predicting academic performance. The proposed framework combines strong predictive performance with interpretability, overcoming the \u201cblack-box\u201d 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\u2019s robustness and generalizability across different educational prediction tasks.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0328634","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:33:03Z","timestamp":1790271183000},"page":"e0328634","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting student academic performance using TabPFN and SHAP: An interpretable machine learning approach"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6708-5722","authenticated-orcid":true,"given":"Qiang","family":"Yin","sequence":"first","affiliation":[{"name":"Shandong Normal University","place":["Jinan, Shandong, China"],"department":["School of Information Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"key":"pone.0328634.ref001","doi-asserted-by":"crossref","DOI":"10.3389\/feduc.2025.1562586","article-title":"The application of machine learning in predicting student performance in university engineering programs: a rapid review","volume":"10","author":"A Turkmenbayev","year":"2025","journal-title":"Front Educ"},{"issue":"1","key":"pone.0328634.ref002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.33736\/jaspe.10465.2026","article-title":"Application of Lightweight Characteristic Residual Frame in Small Sample Score Prediction","volume":"13","author":"M Zhang","year":"2026","journal-title":"J Appl Sci Process Eng"},{"key":"pone.0328634.ref003","doi-asserted-by":"crossref","unstructured":"Hooshyar D, Azevedo R, Yang YJML, Extraction K. Augmenting deep neural networks with symbolic educational knowledge: Towards trustworthy and interpretable ai for education. 2024;6(1):593\u2013618.","DOI":"10.3390\/make6010028"},{"issue":"4","key":"pone.0328634.ref004","doi-asserted-by":"crossref","first-page":"2109","DOI":"10.1007\/s11423-020-09858-2","article-title":"Machine learning for human learners: opportunities, issues, tensions and threats","volume":"69","author":"ME Webb","year":"2020","journal-title":"Education Tech Research Dev"},{"issue":"6","key":"pone.0328634.ref005","doi-asserted-by":"crossref","first-page":"173","DOI":"10.3390\/agriengineering7060173","article-title":"Utilizing TabPFN Transformer with IoT Environmental Data for Early Prediction of Grapevine Diseases","volume":"7","author":"N Arvanitis","year":"2025","journal-title":"AgriEngineering"},{"key":"pone.0328634.ref006","article-title":"Tabpfn: A transformer that solves small tabular classification problems in a second","author":"N Hollmann","year":"2022","journal-title":"Japa"},{"issue":"5","key":"pone.0328634.ref007","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1504\/IJLC.2024.140888","article-title":"Assessment of students\u2019 academic performance in clothing and textile in tertiary institutions using ANN and ANOVA techniques","volume":"16","author":"JE Azonuche","year":"2024","journal-title":"IJLC"},{"issue":"4","key":"pone.0328634.ref008","doi-asserted-by":"crossref","first-page":"187","DOI":"10.4314\/sa.v23i4.17","article-title":"Predicting graduation performance through transformed admission data and first year grades using multiple regression and ANOVA: A case study of Delta State University","volume":"23","author":"SO Ezimadu","year":"2024","journal-title":"sa"},{"key":"pone.0328634.ref009","unstructured":"Ghaleb MMS, Absamatov A, Afaneh JAAJL i B. A Comparative Study of Teaching Methods in Undergraduate Biostatistics Using Regression and ANOVA Techniques. 2025;12(1):67\u201377."},{"issue":"1","key":"pone.0328634.ref010","first-page":"1","article-title":"Forecasting Students\u2019 Academic Performance in Educational Data Using Machine Learning Techniques","volume":"22","author":"N Al-Shanableh","year":"2026","journal-title":"Journal of Educational Data Mining"},{"issue":"1","key":"pone.0328634.ref011","doi-asserted-by":"crossref","DOI":"10.1080\/2331186X.2024.2378508","article-title":"Complex competencies for leader education: artificial intelligence analysis in student achievement profiling","volume":"11","author":"MS Ramirez-Montoya","year":"2024","journal-title":"Cogent Education"},{"key":"pone.0328634.ref012","doi-asserted-by":"crossref","unstructured":"Islam F, Krishna A, Kumar D, Kumari SJM. Factors influencing academic performance: An empirical study using predictive analytics. 2025;3:12.","DOI":"10.62486\/mo202551"},{"key":"pone.0328634.ref013","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.jsp.2019.07.012","article-title":"Students\u2019 academic and emotional adjustment during the transition from primary to secondary school: A cross-lagged study","volume":"76","author":"MC Engels","year":"2019","journal-title":"J Sch Psychol"},{"key":"pone.0328634.ref014","doi-asserted-by":"crossref","unstructured":"Asselman A, Khaldi M, Aammou SJILE. Enhancing the prediction of student performance based on the machine learning XGBoost algorithm. 2023;31(6):3360\u201379.","DOI":"10.1080\/10494820.2021.1928235"},{"key":"pone.0328634.ref015","doi-asserted-by":"crossref","unstructured":"Setiawan I, Gernowo R, Warsito B. Systematic analysis of student academic performance prediction: Prediction model, optimization, data augmentation, and educational policy implications. In: 2024.","DOI":"10.1109\/ICITSI65188.2024.10929265"},{"issue":"10","key":"pone.0328634.ref016","doi-asserted-by":"crossref","first-page":"6199","DOI":"10.3390\/su14106199","article-title":"Predicting Student Outcomes in Online Courses Using Machine Learning Techniques: A Review","volume":"14","author":"A Alhothali","year":"2022","journal-title":"Sustainability"},{"key":"pone.0328634.ref017","doi-asserted-by":"crossref","first-page":"149464","DOI":"10.1109\/ACCESS.2019.2943351","article-title":"Detecting At-Risk Students With Early Interventions Using Machine Learning Techniques","volume":"7","author":"R Al-Shabandar","year":"2019","journal-title":"IEEE Access"},{"key":"pone.0328634.ref018","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s10758-014-9226-4","article-title":"Development and Validation of a Learning Analytics Framework: Two Case Studies Using Support Vector Machines","volume":"19","author":"D Ifenthaler","year":"2014","journal-title":"Tech Know Learn"},{"issue":"1","key":"pone.0328634.ref019","first-page":"80","article-title":"Student performance classification using support vector machine (SVM) with polynomial kernel on online student activities","volume":"23","author":"MH Mohd Zaki","year":"2023","journal-title":"Research ES"},{"key":"pone.0328634.ref020","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.2221","article-title":"Predicting student success in MOOCs: a comprehensive analysis using machine learning models","volume":"10","author":"HA Althibyani","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"pone.0328634.ref021","doi-asserted-by":"crossref","unstructured":"Ismail L, Materwala H, Hennebelle A. Comparative analysis of machine learning models for students\u2019 performance prediction. International Conference on Advances in Digital Science. 2021.","DOI":"10.1007\/978-3-030-71782-7_14"},{"issue":"1","key":"pone.0328634.ref022","first-page":"1","article-title":"Predicting student performance to improve academic advising using the random forest algorithm","volume":"20","author":"M Nachouki","year":"2022","journal-title":"Int J Data Eng Technol"},{"issue":"1","key":"pone.0328634.ref023","first-page":"5731919","article-title":"LSTM\u2010Based Student Performance Prediction Model Incorporating Peer Effects and Explained Through SHAP","volume":"2025","author":"L Zhang","year":"2025","journal-title":"J JoE"},{"key":"pone.0328634.ref024","first-page":"005","article-title":"A Systematic Review of Machine Learning Techniques for Predicting Student Engagement in Higher Education Online Learning","volume":"24","author":"K Ting Chong","year":"2025","journal-title":"JITE:Research"},{"issue":"22","key":"pone.0328634.ref025","doi-asserted-by":"crossref","first-page":"3597","DOI":"10.3390\/math12223597","article-title":"A method for prediction and analysis of student performance that combines multi-dimensional features of time and space","volume":"12","author":"Z Luo","year":"2024","journal-title":"Mathematics"},{"issue":"7","key":"pone.0328634.ref026","doi-asserted-by":"crossref","first-page":"6229","DOI":"10.3390\/su15076229","article-title":"Evaluating student knowledge assessment using machine learning techniques","volume":"15","author":"N Alruwais","year":"2023","journal-title":"Sustainability"},{"issue":"2","key":"pone.0328634.ref027","first-page":"137","article-title":"Student engagement level in an e-learning environment: clustering using k-means","volume":"34","author":"A Moubayed","year":"2020","journal-title":"AJoDE"},{"key":"pone.0328634.ref028","doi-asserted-by":"crossref","unstructured":"Khalil M, Ebner MJJocihe. Clustering patterns of engagement in Massive Open Online Courses (MOOCs): the use of learning analytics to reveal student categories. 2017;29(1):114\u201332.","DOI":"10.1007\/s12528-016-9126-9"},{"key":"pone.0328634.ref029","doi-asserted-by":"crossref","unstructured":"Tao X, Hu J, Wu X, Xia H, editors. Classification of Postgraduate Learning Patterns Based on Cluster Analysis and Its Application in Precision Teaching. Proceedings of the 10th International Conference on Cyber Security and Information Engineering. 2025.","DOI":"10.1145\/3759179.3759188"},{"key":"pone.0328634.ref030","first-page":"100408","article-title":"Learning behavior analysis and personalized recommendation system of online education platform based on machine learning","volume":"8","author":"F Ma","year":"2025","journal-title":"Computers and Education: Artificial Intelligence"},{"key":"pone.0328634.ref031","doi-asserted-by":"crossref","unstructured":"Cam HNT, Tran DATJTJ. Enhancing prediction of student performance based on semi-supervised data augmentation approach. 2026;15(1):678.","DOI":"10.18421\/TEM151-64"},{"issue":"6","key":"pone.0328634.ref032","doi-asserted-by":"crossref","first-page":"7117","DOI":"10.1007\/s10639-024-13111-1","article-title":"Leveraging unlabeled data: Fostering self-regulated learning in online education with semi-supervised recommender systems","volume":"30","author":"L Zhang","year":"2024","journal-title":"Educ Inf Technol"},{"issue":"3","key":"pone.0328634.ref033","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1007\/s40747-022-00647-3","article-title":"Modeling students\u2019 performance using graph convolutional networks","volume":"8","author":"AA Mubarak","year":"2022","journal-title":"Complex Intell Systems"},{"issue":"6","key":"pone.0328634.ref034","doi-asserted-by":"crossref","first-page":"1467","DOI":"10.3233\/IDA-230557","article-title":"Online course evaluation model based on graph auto-encoder","volume":"28","author":"W Yuan","year":"2024","journal-title":"IDA"},{"key":"pone.0328634.ref035","first-page":"100231","article-title":"The power of Deep Learning techniques for predicting student performance in Virtual Learning Environments: A systematic literature review","volume":"6","author":"B Alnasyan","year":"2024","journal-title":"Computers and Education: Artificial Intelligence"},{"key":"pone.0328634.ref036","doi-asserted-by":"crossref","unstructured":"Lumacad GS, Namoco RAJIT o CSS. Multilayer perceptron neural network approach to classifying learning modalities under the new normal. 2023;11(1):1169\u201381.","DOI":"10.1109\/TCSS.2023.3251566"},{"issue":"8","key":"pone.0328634.ref037","first-page":"9989","article-title":"CNN-Transformer: A deep learning method for automatically identifying learning engagement","volume":"29","author":"Y Xiong","year":"2024","journal-title":"Technologies"},{"issue":"2","key":"pone.0328634.ref038","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1108\/AEDS-08-2024-0166","article-title":"Application of machine learning in higher education to predict students\u2019 performance, learning engagement and self-efficacy: a systematic literature review","volume":"14","author":"J Chen","year":"2025","journal-title":"AEDS"},{"issue":"13","key":"pone.0328634.ref039","doi-asserted-by":"crossref","first-page":"19027","DOI":"10.1007\/s10639-025-13526-4","article-title":"Unlocking the power of machine learning in E-learning: A comprehensive review of predictive models for student performance and engagement","volume":"30","author":"M Salem","year":"2025","journal-title":"Educ Inf Technol"},{"issue":"4","key":"pone.0328634.ref040","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/5254.708428","article-title":"Support vector machines","volume":"13","author":"MA Hearst","year":"1998","journal-title":"IEEE Intell Syst Their Appl"},{"issue":"1","key":"pone.0328634.ref041","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"T Cover","year":"1967","journal-title":"IEEE Trans Inform Theory"},{"issue":"5","key":"pone.0328634.ref042","doi-asserted-by":"crossref","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"JH Friedman","year":"2001","journal-title":"Ann Statist"},{"issue":"1","key":"pone.0328634.ref043","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine Learning"},{"issue":"1","key":"pone.0328634.ref044","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1080\/00401706.2000.10485983","article-title":"Ridge regression: biased estimation for nonorthogonal problems","volume":"42","author":"AE Hoerl","year":"2000","journal-title":"Technometrics"},{"key":"pone.0328634.ref045","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016.","DOI":"10.1145\/2939672.2939785"},{"key":"pone.0328634.ref046","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"G Ke","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0328634.ref047","article-title":"Tabpfn: A transformer that solves small tabular classification problems in a second","author":"N Hollmann","year":"2022","journal-title":"arXiv preprint"},{"key":"pone.0328634.ref048","article-title":"A closer look at tabpfn v2: Strength, limitation, and extension","author":"HJ Ye","year":"2025","journal-title":"arXiv preprint"},{"key":"pone.0328634.ref049","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"SM Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0328634.ref050","unstructured":"Rundel D, Kobialka J, von Crailsheim C, Feurer M, Nagler T, R\u00fcgamer D. In: 2024."},{"issue":"1","key":"pone.0328634.ref051","doi-asserted-by":"crossref","first-page":"26879","DOI":"10.1038\/s41598-025-12353-4","article-title":"Machine learning-based academic performance prediction with explainability for enhanced decision-making in educational institutions","volume":"15","author":"W Ahmed","year":"2025","journal-title":"Sci Rep"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:33:20Z","timestamp":1790271200000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328634"}},"subtitle":[],"editor":[{"given":"Wencai","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Jiaotong University: Shanghai Jiao Tong University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":51,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0328634","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,24]]}}}