{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T14:50:33Z","timestamp":1782399033651,"version":"3.54.5"},"reference-count":31,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T00:00:00Z","timestamp":1767484800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Educational Data Mining (EDM) increasingly depends on large, high-quality datasets to drive predictive and adaptive learning systems. However, data scarcity, privacy restrictions, and limited accessibility severely hinder research reproducibility and cross-institutional collaboration. Synthetic data generation provides an emerging solution, enabling the creation of artificial yet statistically realistic datasets that preserve analytical utility while preserving student privacy. This study benchmarks four generative approaches, namely Gaussian Copula, CopulaGAN, Conditional Tabular Generative Adversarial Networks (CTGAN), and Tabular Variational Auto Encoders (TVAE), on student data from six undergraduate courses at a European university. Using the open-source Synthetic Data Vault (SDV) framework, we evaluate the fidelity and Machine Learning utility of synthetic student records through Random Forest classifiers across five metrics, namely accuracy, F1-score, precision, recall, and Area Under Curve (AUC). The results show that synthetic data can achieve 96\u201398% of the predictive performance obtained when training on real data, with TVAE consistently demonstrating the highest multivariate fidelity. Our contributions are threefold: (i) we introduce a reproducible benchmarking pipeline for synthetic data evaluation in educational settings; (ii) we empirically compare statistical and deep generative synthesizers on real-world tabular student data; and (iii) we identify critical research directions related to privacy and reproducibility. The findings position synthetic data generation as a foundational technology for ethical and privacy-preserving EDM.<\/jats:p>","DOI":"10.3390\/a19010039","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T12:38:56Z","timestamp":1767616736000},"page":"39","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking Statistical and Deep Generative Models for Privacy-Preserving Synthetic Student Data in Educational Data Mining"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7374-0099","authenticated-orcid":false,"given":"Georgios","family":"Kostopoulos","sequence":"first","affiliation":[{"name":"Department of Mathematics, University of Patras, 26504 Patras, Greece"},{"name":"School of Social Sciences, Hellenic Open University, 26331 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Tsiakmaki","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Patras, 26504 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2247-3082","authenticated-orcid":false,"given":"Sotiris","family":"Kotsiantis","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Patras, 26504 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,4]]},"reference":[{"key":"ref_1","unstructured":"de Barros, Y.C., and Vilela, J. (2025, January 4\u20136). Data privacy in educational contexts: Analyzing perceptions, practices and challenges in personal data protection. Proceedings of the 27th International Conference on Enterprise Information Systems, ICEIS, Porto, Portugal."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Drachsler, H., and Greller, W. (2016, January 25\u201329). Privacy and analytics: It\u2019s a DELICATE issue a checklist for trusted learning analytics. Proceedings of the Sixth International Conference on Learning Analytics & Knowledge, Edinburgh, UK.","DOI":"10.1145\/2883851.2883893"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Gonzales, A., Guruswamy, G., and Smith, S.R. (2023). Synthetic data in health care: A narrative review. PLoS Digit. Health, 2.","DOI":"10.1371\/journal.pdig.0000082"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Assefa, S.A., Dervovic, D., Mahfouz, M., Tillman, R.E., Reddy, P., and Veloso, M. (2020, January 15\u201316). Generating synthetic data in finance: Opportunities, challenges and pitfalls. Proceedings of the First ACM International Conference on AI in Finance, New York, NY, USA.","DOI":"10.1145\/3383455.3422554"},{"key":"ref_5","first-page":"107","article-title":"The Role of a Reference Synthetic Data Generator within the Field of Learning Analytics","volume":"3","author":"Berg","year":"2016","journal-title":"J. Learn. Anal."},{"key":"ref_6","first-page":"5","article-title":"Synthetic data generator for student data serving learning analytics: A comparative study","volume":"1","author":"Zhan","year":"2023","journal-title":"Learn. Lett."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"100293","DOI":"10.1016\/j.caeai.2024.100293","article-title":"Advancing student outcome predictions through generative adversarial networks","volume":"7","author":"Farhood","year":"2024","journal-title":"Comput. Educ. Artif. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, Q., Khalil, M., Jovanovic, J., and Shakya, R. (2024, January 18\u201322). Scaling while privacy preserving: A comprehensive synthetic tabular data generation and evaluation in learning analytics. Proceedings of the 14th Learning Analytics and Knowledge Conference, Kyoto, Japan.","DOI":"10.1145\/3636555.3636921"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"177345","DOI":"10.1109\/ACCESS.2025.3619091","article-title":"Generative Private Synthetic Student Data for Learning Analytics: An Empirical Study","volume":"13","author":"Iloh","year":"2025","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1111\/bjet.13576","article-title":"Ensuring privacy through synthetic data generation in education","volume":"56","author":"Liu","year":"2025","journal-title":"Br. J. Educ. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, Q., Deho, O., Vadiee, F., Khalil, M., Joksimovic, S., and Siemens, G. (2025, January 3\u20137). Can synthetic data be fair and private? A comparative study of synthetic data generation and fairness algorithms. Proceedings of the 15th International Learning Analytics and Knowledge Conference, Dublin, Ireland.","DOI":"10.1145\/3706468.3706546"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Khalil, M., Vadiee, F., Shakya, R., and Liu, Q. (2025, January 3\u20137). Creating artificial students that never existed: Leveraging large language models and CTGANs for synthetic data generation. Proceedings of the 15th International Learning Analytics and Knowledge Conference, Dublin, Ireland.","DOI":"10.1145\/3706468.3706523"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s44217-025-00743-9","article-title":"FairSYN-Edu: A Diffusion-Based Model for Fair and Private Educational Data Synthesis","volume":"4","author":"Kesgin","year":"2025","journal-title":"Discov. Educ."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kostopoulos, G., Fazakis, N., Kotsiantis, S., and Dimakopoulos, Y. (2025). Enhancing Semi-Supervised Learning in Educational Data Mining Through Synthetic Data Generation Using Tabular Variational Autoencoder. Algorithms, 18.","DOI":"10.3390\/a18100663"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1142\/S0218488502001648","article-title":"K-anonymity: A model for protecting privacy","volume":"10","author":"Sweeney","year":"2002","journal-title":"Int. J. Uncertain. Fuzziness-Knowl.-Based Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3-es","DOI":"10.1145\/1217299.1217302","article-title":"l-diversity: Privacy beyond k-anonymity","volume":"1","author":"Machanavajjhala","year":"2007","journal-title":"ACM Trans. Knowl. Discov. Data (TKDD)"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, N., Li, T., and Venkatasubramanian, S. (2006, January 15\u201320). t-closeness: Privacy beyond k-anonymity and l-diversity. Proceedings of the 2007 IEEE 23rd International Conference on Data Engineering, Istanbul, Turkey.","DOI":"10.1109\/ICDE.2007.367856"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Dwork, C., Hardt, M., Pitassi, T., Reingold, O., and Zemel, R. (2012, January 8\u201310). Fairness through awareness. Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, Cambridge, MA, USA.","DOI":"10.1145\/2090236.2090255"},{"key":"ref_19","unstructured":"Hardt, M., Price, E., and Srebro, N. (2016, January 5\u201310). Equality of opportunity in supervised learning. Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Patki, N., Wedge, R., and Veeramachaneni, K. (2016, January 17\u201319). The Synthetic Data Vault. Proceedings of the 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Montreal, QC, Canada.","DOI":"10.1109\/DSAA.2016.49"},{"key":"ref_21","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative Adversarial Nets. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_22","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-Encoding Variational Bayes. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1561\/2200000056","article-title":"An Introduction to Variational Autoencoders","volume":"12","author":"Kingma","year":"2019","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_24","unstructured":"Xu, L. (2020). Synthesizing Tabular Data Using Conditional GAN. [Ph.D. Thesis, Massachusetts Institute of Technology]."},{"key":"ref_25","unstructured":"Xu, L., Skoularidou, M., Cuesta-Infante, A., and Veeramachaneni, K. (2019, January 8\u201314). Modeling tabular data using conditional gan. Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_26","unstructured":"Jordon, J., Yoon, J., and Van Der Schaar, M. (May, January 30). PATE-GAN: Generating synthetic data with differential privacy guarantees. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_27","unstructured":"Nelsen, R.B. (2006). An Introduction to Copulas, Springer."},{"key":"ref_28","unstructured":"Mirza, M., and Osindero, S. (2014). Conditional Generative Adversarial Nets. arXiv."},{"key":"ref_29","unstructured":"Rezende, D.J., Mohamed, S., and Wierstra, D. (2014, January 22\u201324). Stochastic backpropagation and approximate inference in deep generative models. Proceedings of the International Conference on Machine Learning, Beijing, China."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1080\/01621459.1951.10500769","article-title":"The Kolmogorov\u2013Smirnov Test for Goodness of Fit","volume":"46","author":"Massey","year":"1951","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1007\/BF02589501","article-title":"The Significance Probability of the Smirnov Two-Sample Test","volume":"3","author":"Hodges","year":"1958","journal-title":"Ark. Mat."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/1\/39\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T12:46:34Z","timestamp":1767617194000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/1\/39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,4]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["a19010039"],"URL":"https:\/\/doi.org\/10.3390\/a19010039","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,4]]}}}