{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T13:07:40Z","timestamp":1765458460020,"version":"3.46.0"},"reference-count":54,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"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>Student dropout prediction remains critical in higher education, where timely identification enables effective interventions. Learning Management Systems (LMSs) capture rich temporal data reflecting student behavioral evolution, yet existing approaches underutilize this sequential information. Traditional machine learning methods aggregate behavioral data into static features, discarding dynamic patterns that distinguish successful from at-risk students. While Long Short-Term Memory (LSTM) networks model sequences, they assume discrete time steps and struggle with irregular LMS observation intervals. To address these limitations, we introduce Completion-aware Risk Neural Ordinary Differential Equations (CR-NODE), integrating continuous-time dynamics with completion-focused features for early dropout prediction. CR-NODE employs Neural ODEs to model student behavioral evolution through continuous differential equations, naturally accommodating irregular observation patterns. Additionally, we engineer three completion-focused features: completion rate, early warning score, and engagement variability, derived from root cause analysis. Evaluated on Canvas LMS data from 100,878 enrollments across 89,734 temporal sequences, CR-NODE achieves Macro F1 of 0.8747, significantly outperforming LSTM (0.8123), Extreme Gradient Boosting (XGBoost) (0.8300), and basic Neural ODE (0.8682). McNemar\u2019s test confirms statistical significance (p&lt;0.0001). Cross-dataset validation on the Open University Learning Analytics Dataset (OULAD) demonstrates generalizability, achieving 84.44% accuracy versus state-of-the-art LSTM (83.41%). To support transparent decision-making, SHapley Additive exPlanations (SHAP) analysis reveals completion patterns as the primary prediction drivers.<\/jats:p>","DOI":"10.3390\/a18120781","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T12:57:41Z","timestamp":1765457861000},"page":"781","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Early Student Risk Detection Using CR-NODE: A Completion-Focused Temporal Approach with Explainable AI"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6951-1254","authenticated-orcid":false,"given":"Abdelkarim","family":"Bettahi","sequence":"first","affiliation":[{"name":"AMIPS Research Team, E3S Research Center, Computer Science Department, Mohammadia School of Engineers, Mohammed V University in Rabat, Avenue Ibn Sina B.P. 765, Rabat 10090, Morocco"}]},{"given":"Hamid","family":"Harroud","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, Al Akhawayn University in Ifrane, Ifrane 53000, Morocco"}]},{"given":"Fatima-Zahra","family":"Belouadha","sequence":"additional","affiliation":[{"name":"AMIPS Research Team, E3S Research Center, Computer Science Department, Mohammadia School of Engineers, Mohammed V University in Rabat, Avenue Ibn Sina B.P. 765, Rabat 10090, Morocco"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Romero, C., and Ventura, S. (2020). Educational data mining and learning analytics: An updated survey. WIREs Data Min. Knowl. Discov., 10.","DOI":"10.1002\/widm.1355"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1504\/IJTEL.2012.051816","article-title":"Learning analytics: Drivers, developments and challenges","volume":"4","author":"Ferguson","year":"2012","journal-title":"Int. J. Technol. Enhanc. Learn."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1016\/j.compedu.2009.09.008","article-title":"Mining LMS data to develop an \u201cearly warning system\u201d for educators: A proof of concept","volume":"54","author":"Macfadyen","year":"2010","journal-title":"Comput. Educ."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wolff, A., Zdrahal, Z., Nikolov, A., and Pantucek, M. (2013, January 8\u201312). Improving retention: Predicting at-risk students by analysing clicking behaviour in a virtual learning environment. Proceedings of the Third International Conference on Learning Analytics and Knowledge (LAK \u201913), Leuven, Belgium.","DOI":"10.1145\/2460296.2460324"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/TLT.2016.2616312","article-title":"Predicting Student Performance from LMS Data: A Comparison of 17 Blended Courses Using Moodle LMS","volume":"10","author":"Conijn","year":"2017","journal-title":"IEEE Trans. Learn. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1080\/08839510490442058","article-title":"Predicting students\u2019 performance in distance learning using machine learning techniques","volume":"18","author":"Kotsiantis","year":"2004","journal-title":"Appl. Artif. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.chb.2017.01.047","article-title":"Evaluating the effectiveness of educational data mining techniques for early prediction of students\u2019 academic failure in introductory programming courses","volume":"73","author":"Costa","year":"2017","journal-title":"Comput. Hum. Behav."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Almalawi, A., Soh, B., Li, A., and Samra, H. (2024). Predictive Models for Educational Purposes: A Systematic Review. Big Data Cogn. Comput., 8.","DOI":"10.3390\/bdcc8120187"},{"key":"ref_9","first-page":"1081","article-title":"Predicting Student Dropout in MOOCs Using Genetic Algorithms and XGBoost","volume":"10","author":"Aouarib","year":"2025","journal-title":"J. Inf. Syst. Eng. Manag."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"11499","DOI":"10.1007\/s10639-022-11068-7","article-title":"Dropout prediction in MOOCs using deep learning and machine learning","volume":"27","author":"Basnet","year":"2022","journal-title":"Educ. Inf. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1935","DOI":"10.1002\/int.22129","article-title":"Virtual learning environment to predict withdrawal by leveraging deep learning","volume":"34","author":"Hassan","year":"2019","journal-title":"Int. J. Intell. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Fei, M., and Yeung, D.Y. (2015, January 14\u201317). Temporal Models for Predicting Student Dropout in Massive Open Online Courses. Proceedings of the 2015 IEEE International Conference on Data Mining Workshop (ICDMW), Atlantic City, NJ, USA.","DOI":"10.1109\/ICDMW.2015.174"},{"key":"ref_14","unstructured":"Chen, R.T.Q., Rubanova, Y., Bettencourt, J., and Duvenaud, D.K. (2018, January 2\u20138). Neural Ordinary Differential Equations. Proceedings of the Advances in Neural Information Processing Systems, Montr\u00e9al, QC, Canada."},{"key":"ref_15","unstructured":"Rubanova, Y., Chen, R.T.Q., and Duvenaud, D.K. (2019, January 8\u201314). Latent Ordinary Differential Equations for Irregularly-Sampled Time Series. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1111\/exsy.12135","article-title":"Early dropout prediction using data mining: A case study with high school students","volume":"33","author":"Cano","year":"2016","journal-title":"Expert Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1177\/0002764213479366","article-title":"Learning Analytics: Ethical Issues and Dilemmas","volume":"57","author":"Slade","year":"2013","journal-title":"Am. Behav. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1007\/s40593-021-00239-1","article-title":"Ethics of AI in Education: Towards a Community-Wide Framework","volume":"32","author":"Holmes","year":"2022","journal-title":"Int. J. Artif. Intell. Educ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEE Access"},{"key":"ref_20","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). A Unified Approach to Interpreting Model Predictions. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"111","DOI":"10.62762\/JSSPA.2025.321501","article-title":"Student Dropout Prediction Using Ensemble Learning with SHAP-Based Explainable AI Analysis","volume":"2","author":"Liu","year":"2025","journal-title":"J. Soc. Syst. Policy Anal."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/BF02295996","article-title":"Note on the sampling error of the difference between correlated proportions or percentages","volume":"12","author":"McNemar","year":"1947","journal-title":"Psychometrika"},{"key":"ref_23","unstructured":"Arnold, K.E., and Pistilli, M.D. (May, January 29). Course signals at Purdue: Using learning analytics to increase student success. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (LAK \u201912), Vancouver, BC, Canada."},{"key":"ref_24","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_25","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1016\/j.compedu.2009.05.010","article-title":"Dropout prediction in e-learning courses through the combination of machine learning techniques","volume":"53","author":"Lykourentzou","year":"2009","journal-title":"Comput. Educ."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Whitehill, J., Mohan, K., Seaton, D., Rosen, Y., and Tingley, D. (2017). Delving Deeper into MOOC Student Dropout Prediction. arXiv.","DOI":"10.1145\/3051457.3053974"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, W., Yu, H., and Miao, C. (2017, January 6\u20139). Deep Model for Dropout Prediction in MOOCs. Proceedings of the 2nd International Conference on Crowd Science and Engineering (ICCSE\u201917), Beijing, China.","DOI":"10.1145\/3126973.3126990"},{"key":"ref_28","unstructured":"Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L.J., and Sohl-Dickstein, J. (2015, January 7\u201312). Deep Knowledge Tracing. Proceedings of the Advances in Neural Information Processing Systems, Montr\u00e9al, QC, Canada."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yeung, C.K., and Yeung, D.Y. (2018, January 26\u201328). Addressing two problems in deep knowledge tracing via prediction-consistent regularization. Proceedings of the Fifth Annual ACM Conference on Learning at Scale (L@S \u201918), London, UK.","DOI":"10.1145\/3231644.3231647"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"55146","DOI":"10.1109\/ACCESS.2024.3388718","article-title":"DKVMN-KAPS: Dynamic Key-Value Memory Networks Knowledge Tracing with Students\u2019 Knowledge-Absorption Ability and Problem-Solving Ability","volume":"12","author":"Zhang","year":"2024","journal-title":"IEEE Access"},{"key":"ref_31","unstructured":"Dupont, E., Doucet, A., and Teh, Y.W. (2019, January 8\u201314). Augmented Neural ODEs. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_32","unstructured":"Kidger, P., Morrill, J., Foster, J., and Lyons, T. (2020, January 6\u201312). Neural Controlled Differential Equations for Irregular Time Series. Proceedings of the Advances in Neural Information Processing Systems, Virtual."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201916), San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_34","unstructured":"Graf, S., and Markos, A. (2025). Counterfactual Fairness Evaluation of Machine Learning Models on Educational Datasets. Generative Systems and Intelligent Tutoring Systems, Springer."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Song, Y., Li, C., Xing, W., Lyu, B., and Zhu, W. (2025). Investigating perceived fairness of AI prediction system for math learning: A mixed-methods study with college students. Internet High. Educ., 65.","DOI":"10.1016\/j.iheduc.2025.101000"},{"key":"ref_36","unstructured":"Cristea, A.I., Walker, E., Lu, Y., Santos, O.C., and Isotani, S. (2025). Privacy-Preserving Federated Learning for Student Dropout Prediction: Enhancing Model Transparency with Explainable AI. Artificial Intelligence in Education, Springer Nature."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Saito, T., and Rehmsmeier, M. (2015). The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0118432"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal Loss for Dense Object Detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_39","unstructured":"Loshchilov, I., and Hutter, F. (2019, January 6\u20139). Decoupled Weight Decay Regularization. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1162\/089976698300017197","article-title":"Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms","volume":"10","author":"Dietterich","year":"1998","journal-title":"Neural Comput."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1016\/j.chb.2013.05.031","article-title":"Can we predict success from log data in VLEs? Classification of interactions for learning analytics and their relation with performance in VLE-supported F2F and online learning","volume":"31","year":"2014","journal-title":"Comput. Hum. Behav."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1007\/s11528-014-0822-x","article-title":"Let\u2019s not forget: Learning analytics are about learning","volume":"59","author":"Dawson","year":"2015","journal-title":"TechTrends"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Kuzilek, J., Hlosta, M., and Zdrahal, Z. (2017). Open University Learning Analytics dataset. Sci. Data, 4.","DOI":"10.1038\/sdata.2017.171"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Torkhani, W., and Rezgui, K. (2024, January 31). OULAD MOOC Student Performance Prediction using Machine and Deep Learning Techniques. Proceedings of the International Conference on Decision Aid and Artificial Intelligence (ICODAI 2024), Alecso, Tunisia.","DOI":"10.2991\/978-94-6463-654-3_18"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/TETC.2015.2504239","article-title":"Identifying At-Risk Students for Early Interventions\u2014A Time-Series Clustering Approach","volume":"5","author":"Hung","year":"2017","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Liu, Y., Fan, S., Xu, S., Sajjanhar, A., Yeom, S., and Wei, Y. (2023). Predicting Student Performance Using Clickstream Data and Machine Learning. Educ. Sci., 13.","DOI":"10.3390\/educsci13010017"},{"key":"ref_47","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is All you Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., and Elhadad, N. (2015, January 10\u201313). Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201915), Sydney, Australia.","DOI":"10.1145\/2783258.2788613"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Chang, Y.H., Chen, F.C., and Lee, C.I. (2025). Developing an Early Warning System with Personalized Interventions to Enhance Academic Outcomes for At-Risk Students in Taiwanese Higher Education. Educ. Sci., 15.","DOI":"10.3390\/educsci15101321"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.compedu.2015.03.020","article-title":"The effect of blended learning on course persistence and performance of adult learners: A difference-in-differences analysis","volume":"87","author":"Deschacht","year":"2015","journal-title":"Comput. Educ."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.compedu.2019.04.001","article-title":"The role of demographics in online learning; A decision tree based approach","volume":"137","author":"Rizvi","year":"2019","journal-title":"Comput. Educ."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"102","DOI":"10.18608\/jla.2023.7975","article-title":"Student Privacy and Learning Analytics: Investigating the Application of Privacy Within a Student Success Information System in Higher Education","volume":"10","author":"Francis","year":"2023","journal-title":"J. Learn. Anal."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Turkmenbayev, A., Abdykerimova, E., Nurgozhayev, S., Karabassova, G., and Baigozhanova, D. (2025). The application of machine learning in predicting student performance in university engineering programs: A rapid review. Front. Educ., 10.","DOI":"10.3389\/feduc.2025.1562586"},{"key":"ref_54","unstructured":"Gao, T., Sun, S., Liu, H., and Gao, H. (2025, January 24\u201328). Exploring the Impact of Activation Functions in Training Neural ODEs. Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025), Singapore."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/12\/781\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T13:01:44Z","timestamp":1765458104000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/12\/781"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,11]]},"references-count":54,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["a18120781"],"URL":"https:\/\/doi.org\/10.3390\/a18120781","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,11]]}}}