{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T10:50:35Z","timestamp":1774003835518,"version":"3.50.1"},"reference-count":38,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Deanship of Graduate Studies and Scientific Research at University of Bisha"},{"name":"Fast-Track Research Support Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Massive Open Online Courses (MOOCs) offer access to high-scalable and flexible education to diverse people in distant parts of the world, yet persistently plagued by high dropout rates. To operationalize this problem, more correct and interpretable models need to be created, which operate on heterogeneous and vertically integrated educational data. Here, the method is a hybrid explainable deep learning model, used to predict Dropout in MOOCs. The student activity logs, course metadata, and assessment records used in the framework are combined through integration with an unbalanced assignment to ensure that imbalanced data are balanced out with the application of Generative Adversarial Network (GAN). To facilitate complex behavioral patterns related to Dropout, we come up with a multi-head attention neural network that represents both temporal and contextual aspects. To provide interpretability, we acquire local explanations with Local Interpretable Model-agnostic Explanations (LIME) and global cohort-level representativeness on the basis of the attention mechanism. The combination of these explanations is carried out by a new hybrid algorithm that offers a population level reformulation as well as a student-level ratification of predictions. On the benchmark Knowledge Discovery and Data Mining (KDD Cup) 2015 dataset, the proposed VertiDaX gives an excellent F1-score and receiver operating characteristic area under the curve (ROC-AUC), which are better than earlier baselines. The study also used the Open University Learning Analytics Dataset (OULAD) data to stratify cross validate on the same label scheme, where we evaluate generalisation and stability in moderate class imbalance. The explained method captures common and personalized behavioral patterns associated with dropout, with a view to establishing educator-specific intervention strategies. This project represents a stepping stone in showing that GAN-based data augmentation plus attention-based deep learning and hybrid interpretation is a formula that will offer valuable and concrete results in predicting dropout rates in MOOCs. We propose the exciting future use of interpretable artificial intelligence (AI) that can be implemented in scalable online training based on the findings.<\/jats:p>","DOI":"10.7717\/peerj-cs.3718","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T08:34:11Z","timestamp":1773995651000},"page":"e3718","source":"Crossref","is-referenced-by-count":0,"title":["VertiDaX: an explainable hybrid deep learning model for dropout prediction with vertical integration"],"prefix":"10.7717","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3315-5952","authenticated-orcid":true,"given":"Mohammad","family":"Waseem","sequence":"first","affiliation":[{"name":"Department of Computer Science, Aligarh Muslim University, Aligarh, Uttar Pradesh, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shafiqul","family":"Abidin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aligarh Muslim University, Aligarh, Uttar Pradesh, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0668-9796","authenticated-orcid":true,"given":"Mahfooz","family":"Alam","sequence":"additional","affiliation":[{"name":"Department of MCA, G. L. Bajaj Institute of Technology and Management, Greater Noida, Uttar Pradesh, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4864-9485","authenticated-orcid":true,"given":"Mohd Shahid","family":"Husain","sequence":"additional","affiliation":[{"name":"College of Computing and Information Sciences, University of Applied Science and Technology, Ibri, Oman"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1552-315X","authenticated-orcid":true,"given":"Mohammad Zunnun","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Information Systems and Cybersecurity, University of Bisha, Bisha, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7122-2856","authenticated-orcid":true,"given":"Zubair","family":"Ashraf","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, University of Bisha, Bisha, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"10.7717\/peerj-cs.3718\/ref-1","first-page":"663","article-title":"Machine learning in cybersecurity: opportunities and challenges","author":"Alam","year":"2024"},{"issue":"2","key":"10.7717\/peerj-cs.3718\/ref-2","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/s12528-019-09241-y","article-title":"Factors affecting student dropout in MOOCs: a cause and effect decision-making model","volume":"32","author":"Aldowah","year":"2020","journal-title":"Journal of Computing in Higher Education"},{"key":"10.7717\/peerj-cs.3718\/ref-3","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-030-31284-8_10","article-title":"Explainable artificial intelligence for human-centric data analysis in virtual learning environments","volume-title":"Higher Education Learning Methodologies and Technologies Online","author":"Alonso","year":"2019"},{"key":"10.7717\/peerj-cs.3718\/ref-4","first-page":"13","article-title":"Interpretable deep learning for university dropout prediction","author":"Baranyi","year":"2020"},{"issue":"1","key":"10.7717\/peerj-cs.3718\/ref-5","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/3359786","article-title":"Techniques for interpretable machine learning","volume":"63","author":"Du","year":"2019","journal-title":"Communications of the ACM"},{"key":"10.7717\/peerj-cs.3718\/ref-6","first-page":"256","article-title":"Temporal models for predicting student dropout in massive open online courses","author":"Fei","year":"2015"},{"key":"10.7717\/peerj-cs.3718\/ref-7","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1609\/aaai.v33i01.3301517","article-title":"Understanding dropouts in MOOCs","volume":"33","author":"Feng","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.7717\/peerj-cs.3718\/ref-8","doi-asserted-by":"publisher","first-page":"107315","DOI":"10.1016\/j.compeleceng.2021.107315","article-title":"CLSA: a novel deep learning model for MOOC dropout prediction","volume":"94","author":"Fu","year":"2021","journal-title":"Computers & Electrical Engineering"},{"key":"10.7717\/peerj-cs.3718\/ref-9","doi-asserted-by":"publisher","first-page":"100074","DOI":"10.1016\/j.caeai.2022.100074","article-title":"Explainable artificial intelligence in education","volume":"3","author":"Khosravi","year":"2022","journal-title":"Computers and Education: Artificial Intelligence"},{"key":"10.7717\/peerj-cs.3718\/ref-10","doi-asserted-by":"publisher","first-page":"120933","DOI":"10.1016\/j.eswa.2023.120933","article-title":"An explainable machine learning approach for student dropout prediction","volume":"233","author":"Kr\u00fcger","year":"2023","journal-title":"Expert Systems with Applications"},{"issue":"2","key":"10.7717\/peerj-cs.3718\/ref-11","doi-asserted-by":"publisher","first-page":"187","DOI":"10.32985\/ijeces.14.2.8","article-title":"Ensemble deep learning network model for dropout prediction in MOOCs","volume":"14","author":"Kumar","year":"2023","journal-title":"International Journal of Electrical and Computer Engineering Systems"},{"key":"10.7717\/peerj-cs.3718\/ref-12","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1007\/978-3-031-98465-5_41","article-title":"Privacy-preserving federated learning for student dropout prediction: enhancing model transparency with explainable AI","volume-title":"Artificial Intelligence in Education","author":"Lamsiyah","year":"2025"},{"issue":"1","key":"10.7717\/peerj-cs.3718\/ref-13","doi-asserted-by":"publisher","first-page":"103536","DOI":"10.1016\/j.ipm.2023.103536","article-title":"Quantification and prediction of engagement: applied to personalized course recommendation to reduce dropout in MOOCs","volume":"61","author":"Li","year":"2024","journal-title":"Information Processing & Management"},{"issue":"6","key":"10.7717\/peerj-cs.3718\/ref-14","doi-asserted-by":"publisher","first-page":"1867","DOI":"10.1002\/cae.22678","article-title":"Research on the big data analysis of MOOCs in a flipped classroom based on attention mechanism in deep learning model","volume":"31","author":"Li","year":"2023","journal-title":"Computer Applications in Engineering Education"},{"issue":"3","key":"10.7717\/peerj-cs.3718\/ref-15","doi-asserted-by":"publisher","first-page":"3257","DOI":"10.1007\/s10639-023-11960-w","article-title":"Learning behavior feature fused deep learning network model for MOOC dropout prediction","volume":"29","author":"Liu","year":"2024","journal-title":"Education and Information Technologies"},{"key":"10.7717\/peerj-cs.3718\/ref-16","first-page":"295","article-title":"A weighted feature extraction technique based on temporal accumulation of learner behavior features for early prediction of dropouts","author":"Liu","year":"2020"},{"key":"10.7717\/peerj-cs.3718\/ref-17","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"10.7717\/peerj-cs.3718\/ref-18","first-page":"3","article-title":"VulEXplaineR: XAI for vulnerability detection on assembly code","author":"Mahdavifar","year":"2024"},{"issue":"4","key":"10.7717\/peerj-cs.3718\/ref-19","doi-asserted-by":"publisher","first-page":"72","DOI":"10.14313\/JAMRIS\/4-2020\/48","article-title":"A dropout predictor system in MOOCs based on neural networks","volume":"14","author":"Mrhar","year":"2021","journal-title":"Journal of Automation, Mobile Robotics and Intelligent Systems"},{"key":"10.7717\/peerj-cs.3718\/ref-20","doi-asserted-by":"publisher","first-page":"107271","DOI":"10.1016\/j.compeleceng.2021.107271","article-title":"Deep analytic model for student dropout prediction in massive open online courses","volume":"93","author":"Mubarak","year":"2021","journal-title":"Computers & Electrical Engineering"},{"issue":"4","key":"10.7717\/peerj-cs.3718\/ref-21","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1002\/cae.22328","article-title":"Visual analytics of video-clickstream data and prediction of learners\u2019 performance using deep learning models in MOOCs\u2019 courses","volume":"29","author":"Mubarak","year":"2021","journal-title":"Computer Applications in Engineering Education"},{"key":"10.7717\/peerj-cs.3718\/ref-22","first-page":"1695","article-title":"Generative adversarial minority oversampling","author":"Mullick","year":"2019"},{"key":"10.7717\/peerj-cs.3718\/ref-23","first-page":"346","article-title":"Software defects prediction using generative adversarial network based data balancing","author":"Mustaqeem","year":"2024"},{"issue":"4","key":"10.7717\/peerj-cs.3718\/ref-24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.58414\/scientifictemper.2024.15.2.32","article-title":"Predictive modeling of dropout in MOOCs using machine learning techniques","volume":"12","author":"Patel","year":"2024","journal-title":"International Journal of Intelligent Systems and Applications in Engineering"},{"key":"10.7717\/peerj-cs.3718\/ref-25","first-page":"1135","article-title":"\u201cwhy should i trust you?\u201d Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"10.7717\/peerj-cs.3718\/ref-26","first-page":"130","article-title":"MalGPT: a generative explainable model for malware binaries","author":"Saqib","year":"2026"},{"issue":"4","key":"10.7717\/peerj-cs.3718\/ref-27","doi-asserted-by":"publisher","first-page":"1828","DOI":"10.1016\/j.asr.2024.05.023","article-title":"Seismo-ionospheric precursory detection using hybrid Bayesian-LSTM network model with uncertainty-boundaries and anomaly-intensity","volume":"74","author":"Saqib","year":"2024","journal-title":"Advances in Space Research"},{"key":"10.7717\/peerj-cs.3718\/ref-28","first-page":"979","article-title":"Modeling student learning styles in MOOCs","author":"Shi","year":"2017"},{"key":"10.7717\/peerj-cs.3718\/ref-29","first-page":"353","article-title":"Time series model for predicting dropout in massive open online courses","author":"Tang","year":"2018"},{"key":"10.7717\/peerj-cs.3718\/ref-30","first-page":"419","article-title":"Learning behavior analysis and dropout rate prediction based on MOOCs data","author":"Wang","year":"2019"},{"issue":"10","key":"10.7717\/peerj-cs.3718\/ref-31","doi-asserted-by":"publisher","first-page":"7102","DOI":"10.1080\/10494820.2023.2300000","article-title":"Early prediction of MOOC dropout in self-paced students using deep learning","volume":"32","author":"Wen","year":"2024","journal-title":"Interactive Learning Environments"},{"issue":"3","key":"10.7717\/peerj-cs.3718\/ref-32","doi-asserted-by":"publisher","first-page":"336","DOI":"10.26599\/tst.2019.9010013","article-title":"Consideration of the local correlation of learning behaviors to predict dropouts from MOOCs","volume":"25","author":"Wen","year":"2019","journal-title":"Tsinghua Science and Technology"},{"issue":"10","key":"10.7717\/peerj-cs.3718\/ref-33","doi-asserted-by":"publisher","first-page":"2471","DOI":"10.14778\/3603581.3603588","article-title":"Falcon: a privacy-preserving and interpretable vertical federated learning system","volume":"16","author":"Wu","year":"2023","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"3","key":"10.7717\/peerj-cs.3718\/ref-34","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1177\/0735633118757015","article-title":"Dropout prediction in MOOCs: using deep learning for personalized intervention","volume":"57","author":"Xing","year":"2019","journal-title":"Journal of Educational Computing Research"},{"issue":"5","key":"10.7717\/peerj-cs.3718\/ref-35","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1109\/jstsp.2017.2700227","article-title":"Behavior-based grade prediction for MOOCs via time series neural networks","volume":"11","author":"Yang","year":"2017","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"10.7717\/peerj-cs.3718\/ref-36","doi-asserted-by":"publisher","first-page":"202993\u2013203002","DOI":"10.1109\/access.2020.3035687","article-title":"Power of attention in MOOC dropout prediction","volume":"8","author":"Yin","year":"2020","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3718\/ref-37","doi-asserted-by":"publisher","first-page":"225324\u2013225335","DOI":"10.1109\/access.2020.3045157","article-title":"MOOC dropout prediction using FWTS-CNN model based on fused feature weighting and time series","volume":"8","author":"Zheng","year":"2020","journal-title":"IEE Access"},{"key":"10.7717\/peerj-cs.3718\/ref-38","doi-asserted-by":"publisher","first-page":"108409","DOI":"10.1016\/j.compeleceng.2022.108409","article-title":"MOOC dropout prediction using a fusion deep model based on behaviour features","volume":"104","author":"Zheng","year":"2022","journal-title":"Computers and Electrical Engineering"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3718.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3718.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3718.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3718.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T08:34:15Z","timestamp":1773995655000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3718"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":38,"alternative-id":["10.7717\/peerj-cs.3718"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3718","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]},"article-number":"e3718"}}