{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T23:41:11Z","timestamp":1776814871775,"version":"3.51.2"},"reference-count":38,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan","award":["AP23489228"],"award-info":[{"award-number":["AP23489228"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Educational equity and access to quality learning opportunities represent fundamental pillars of sustainable societal development, directly aligned with the United Nations Sustainable Development Goal 4 (Quality Education). Student retention remains a critical challenge in higher education, with early disengagement strongly predicting eventual failure and limiting opportunities for social mobility. While machine learning models have demonstrated impressive predictive accuracy for identifying at-risk students, most systems prioritize performance metrics over practical deployment constraints, creating a gap between research demonstrations and real-world impact for social good. We present an accountable and interpretable decision support system that balances three competing objectives essential for responsible AI deployment: ultra-early prediction timing (day 14 of semester), manageable instructor workload (flagging 15% of students), and model transparency (multiple explanation mechanisms). Using the Open University Learning Analytics Dataset (OULAD) containing 22,437 students across seven modules, we develop predictive models from activity patterns, assessment performance, and demographics observable within two weeks. We compare threshold-based rules, logistic regression (interpretable linear modeling), and gradient boosting (ensemble modeling) using temporal validation where early course presentations train models tested on later cohorts. Results show gradient boosting achieves AUC (Area Under the ROC Curve, measuring discrimination ability) of 0.789 and average precision of 0.722, with logistic regression performing nearly identically (AUC 0.783, AP 0.713), revealing that linear modeling captures most predictive signal and makes interpretability essentially free. At our recommended threshold of 0.607, the predictive model flags 15% of students with 84% precision and 35% recall, creating actionable alert lists instructors can manage within normal teaching duties while maintaining accountability for false positives. Calibration analysis confirms that predicted probabilities match observed failure rates, ensuring trustworthy risk estimates. Feature importance modeling reveals that assessment completion and activity patterns dominate demographic factors, providing transparent evidence that behavioral engagement matters more than student background. We implement a complete decision support system generating instructor reports, explainable natural language justifications for each alert, and personalized intervention templates. Our contribution advances responsible AI for social good by demonstrating that interpretable predictive modeling can support equitable educational outcomes when designed with explicit attention to timing, workload, and transparency\u2014core principles of accountable artificial intelligence.<\/jats:p>","DOI":"10.3390\/bdcc9110297","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T09:44:53Z","timestamp":1763631893000},"page":"297","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Interpretable Predictive Modeling for Educational Equity: A Workload-Aware Decision Support System for Early Identification of At-Risk Students"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6006-4813","authenticated-orcid":false,"given":"Aigul","family":"Shaikhanova","sequence":"first","affiliation":[{"name":"Department of Information Security, L.N. Gumilyov Eurasian National University, Satpayev 2, 010008 Astana, Kazakhstan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2331-6326","authenticated-orcid":false,"given":"Oleksandr","family":"Kuznetsov","sequence":"additional","affiliation":[{"name":"Department of Theoretical and Applied Sciences, eCampus University, Via Isimbardi 10, 22060 Novedrate, CO, Italy"},{"name":"Department of Intelligent Software Systems and Technologies, School of Computer Science and Artificial Intelligence, V. N. Karazin Kharkiv National University, 4 Svobody Sq., 61022 Kharkiv, Ukraine"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8330-4282","authenticated-orcid":false,"given":"Kainizhamal","family":"Iklassova","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Technologies, Manash Kozybayev North Kazakhstan University, Pushkin Str., 86, 150000 Petropavlovsk, Kazakhstan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5019-2413","authenticated-orcid":false,"given":"Aizhan","family":"Tokkuliyeva","sequence":"additional","affiliation":[{"name":"Department of Information Security, L.N. Gumilyov Eurasian National University, Satpayev 2, 010008 Astana, Kazakhstan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4784-9952","authenticated-orcid":false,"given":"Laura","family":"Sugurova","sequence":"additional","affiliation":[{"name":"Department of Automation and Telecommunications, M.Kh. Dulati Taraz University, Tole bi 60, 080002 Taraz, Kazakhstan"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"ref_1","unstructured":"(2015). Supporting the Sustainable Development Goals, African Promise."},{"key":"ref_2","unstructured":"European Education and Culture Executive Agency, Eurydice (2024). The Structure of the European Education Systems, European Education and Culture Executive Agency, Eurydice."},{"key":"ref_3","unstructured":"Liu, N., Feng, Z., and Wang, Q. (2024). Global Comparison of Education Systems. Education in China and the World: Achievements and Contemporary Issues, Springer Nature."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"100043","DOI":"10.1016\/j.ijedro.2021.100043","article-title":"High Achievement for Socio-economically Disadvantaged Students: Example of an Equitable Education Model in Schools across Five English Districts","volume":"2","author":"Cockerill","year":"2021","journal-title":"Int. J. Educ. Res. Open"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Symonds, J.E., Chzhen, Y., Kaye, N., Dominy, J., Campbell, C., Sykes, C., Ba\u015ftu\u011f, S.I., Fiasconaro, S., and Heydari Barardehi, I. (2025). A Metareview of Research on Educational Inequality and Socioeconomic Disadvantage. Educ. Sci., 15.","DOI":"10.3390\/educsci15060740"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hafdi, Z.S., and El Kafhali, S. (2025). A Comparative Evaluation of Machine Learning Methods for Predicting Student Outcomes in Coding Courses. AppliedMath, 5.","DOI":"10.3390\/appliedmath5020075"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"108183","DOI":"10.1016\/j.chb.2024.108183","article-title":"Exploring the Relationship between LMS Interactions and Academic Performance: A Learning Cycle Approach","volume":"155","year":"2024","journal-title":"Comput. Hum. Behav."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Shanto, S.S., and Jony, A.I. (2025). Interpretable Ensemble Learning Approach for Predicting Student Adaptability in Online Education Environments. Knowledge, 5.","DOI":"10.3390\/knowledge5020010"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"200352","DOI":"10.1016\/j.sasc.2025.200352","article-title":"Predicting Student Retention: A Comparative Study of Machine Learning Approach Utilizing Sociodemographic and Academic Factors","volume":"7","author":"Dia","year":"2025","journal-title":"Syst. Soft Comput."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gligorea, I., Yaseen, M.U., Cioca, M., Gorski, H., and Oancea, R. (2022). An Interpretable Framework for an Efficient Analysis of Students\u2019 Academic Performance. Sustainability, 14.","DOI":"10.3390\/su14148885"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103398","DOI":"10.1016\/j.ijedudev.2025.103398","article-title":"Bridging EdTech Gaps: Examining Learning Equity in Low-Income Educational Settings","volume":"118","author":"Bawa","year":"2025","journal-title":"Int. J. Educ. Dev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"100244","DOI":"10.1016\/j.caeai.2024.100244","article-title":"Enhancing Educational Evaluation through Predictive Student Assessment Modeling","volume":"6","author":"Mai","year":"2024","journal-title":"Comput. Educ. Artif. Intell."},{"key":"ref_13","unstructured":"Doan, N., Cooke, M.J., Wallace, M.P., Neiterman, E., and Lee Olstad, D. Intersections of Educational Attainment, Indigenous Identity and Race\/Ethnicity Best Predicted Diet Quality among Adults in Canada: A Conditional Random Forests Analysis, J. Acad. Nutr. Diet., in press."},{"key":"ref_14","first-page":"151","article-title":"Indicators-Markers for Assessment of Probability of Insurance Companies Relatedness in Implementation of Risk-Oriented Approach","volume":"29","author":"Vnukova","year":"2020","journal-title":"Econ. Stud. J."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kavun, S., Zamula, A., and Mikheev, I. (2017, January 10\u201313). Calculation of Expense for Local Computer Networks. Proceedings of the 2017 4th International Scientific-Practical Conference Problems of Infocommunications. Science and Technology (PIC S&T), Kharkov, Ukraine.","DOI":"10.1109\/INFOCOMMST.2017.8246369"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4028","DOI":"10.1016\/j.sbspro.2011.04.408","article-title":"A Sample Study on Applying Data Mining Research Techniques in Educational Science: Developing a More Meaning of Data","volume":"15","author":"Zengin","year":"2011","journal-title":"Procedia-Soc. Behav. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"108155","DOI":"10.1016\/j.chb.2024.108155","article-title":"Reviewing the Differences between Learning Analytics and Educational Data Mining: Towards Educational Data Science","volume":"154","author":"Cerezo","year":"2024","journal-title":"Comput. Hum. Behav."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.iheduc.2015.11.003","article-title":"Identifying Significant Indicators Using LMS Data to Predict Course Achievement in Online Learning","volume":"29","author":"You","year":"2016","journal-title":"Internet High. Educ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100175","DOI":"10.1016\/j.caeai.2023.100175","article-title":"Accurate, Timely, and Portable: Course-Agnostic Early Prediction of Student Performance from LMS Logs","volume":"5","author":"Santos","year":"2023","journal-title":"Comput. Educ. Artif. Intell."},{"key":"ref_20","first-page":"516","article-title":"Interpretable AI Techniques Unveil the Factors and Types of At-Risk Early Warning: A Case Study in K-12 Online Learning","volume":"59","author":"Hung","year":"2025","journal-title":"Data Technol. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhang, C., and Ahn, H. (2023). E-Learning at-Risk Group Prediction Considering the Semester and Realistic Factors. Educ. Sci., 13.","DOI":"10.3390\/educsci13111130"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e30960","DOI":"10.1016\/j.heliyon.2024.e30960","article-title":"Predictive Modelling of Student Dropout Risk: Practical Insights from a South Korean Distance University","volume":"10","author":"Seo","year":"2024","journal-title":"Heliyon"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3223","DOI":"10.1016\/j.procs.2023.10.316","article-title":"Predicting Students at Risk of Early Dropping Out from Course Using Ensemble Classification Methods","volume":"225","author":"Pecuchova","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Queiroga, E.M., Batista Machado, M.F., Paragarino, V.R., Primo, T.T., and Cechinel, C. (2022). Early Prediction of At-Risk Students in Secondary Education: A Countrywide K-12 Learning Analytics Initiative in Uruguay. Information, 13.","DOI":"10.3390\/info13090401"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Santana-Perera, B., Garc\u00eda-Barcel\u00f3, C., Gonz\u00e1lez Arcas, M., and Gil, D. (2025). Exploring Predictive Insights on Student Success Using Explainable Machine Learning: A Synthetic Data Study. Information, 16.","DOI":"10.3390\/info16090763"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"114229","DOI":"10.1016\/j.dss.2024.114229","article-title":"Explainable Learning Analytics: Assessing the Stability of Student Success Prediction Models by Means of Explainable AI","volume":"182","author":"Tiukhova","year":"2024","journal-title":"Decis. Support Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3211","DOI":"10.32604\/cmc.2022.023560","article-title":"Interpretable and Adaptable Early Warning Learning Analytics Model","volume":"71","author":"Sohail","year":"2021","journal-title":"CMC"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"\u010coti\u0107 Poturi\u0107, V., \u010candrli\u0107, S., and Dra\u017ei\u0107, I. (2025). A Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses. Algorithms, 18.","DOI":"10.3390\/a18040177"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105384","DOI":"10.1016\/j.compedu.2025.105384","article-title":"Prescriptive Analytics for Student Success in an Online University: Drawing Learning Profiles from Trace Observations for Tailored Support","volume":"237","author":"Seo","year":"2025","journal-title":"Comput. Educ."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"100103","DOI":"10.1016\/j.caeai.2022.100103","article-title":"A Flexible Feature Selection Approach for Predicting Students\u2019 Academic Performance in Online Courses","volume":"3","author":"Peumans","year":"2022","journal-title":"Comput. Educ. Artif. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"101728","DOI":"10.1016\/j.jksuci.2023.101728","article-title":"SMFSOP: A Semantic-Based Modelling Framework for Student Outcome Prediction","volume":"35","author":"Hassan","year":"2023","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"100300","DOI":"10.1016\/j.caeai.2024.100300","article-title":"Latent Space Bias Mitigation for Predicting At-Risk Students","volume":"7","author":"Peumans","year":"2024","journal-title":"Comput. Educ. Artif. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"107933","DOI":"10.1016\/j.infsof.2025.107933","article-title":"Trade-Offs between Fairness and Performance in Educational AI: Analyzing Post-Processing Bias Mitigation on the OULAD","volume":"189","author":"Gunasekara","year":"2026","journal-title":"Inf. Softw. Technol."},{"key":"ref_34","first-page":"200483","article-title":"Exploring the VAK Model to Predict Student Learning Styles Based on Learning Activity","volume":"25","author":"Sayed","year":"2025","journal-title":"Intell. Syst. Appl."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2444","DOI":"10.1016\/j.procs.2022.09.302","article-title":"Using Behavioral Primitives to Model Students\u2019 Digital Behavior","volume":"207","author":"Dermy","year":"2022","journal-title":"Procedia Comput. Sci."},{"key":"ref_36","unstructured":"Jakub Kuzilek, M.H., Hlosta, M., and Zdrahal, Z. (2015). Open University Learning Analytics Dataset, UCI Machine Learning Repository."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"170171","DOI":"10.1038\/sdata.2017.171","article-title":"Open University Learning Analytics Dataset","volume":"4","author":"Kuzilek","year":"2017","journal-title":"Sci. Data"},{"key":"ref_38","unstructured":"(2025, October 01). Open University Learning Analytics Dataset (OULAD). Available online: https:\/\/www.kaggle.com\/datasets\/anlgrbz\/student-demographics-online-education-dataoulad."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/11\/297\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T10:43:23Z","timestamp":1763635403000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/11\/297"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":38,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["bdcc9110297"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9110297","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,20]]}}}