Keywords
participation risk
community education
early warning
XGBoost
SHAP
learner retention
educational intervention
Abstract
This study develops a predictive learning analytics model to identify participation risk in community education programs before learners become inactive or withdraw. The study is designed to collect data from approximately 1,200 learners across 36 community education programs over two semesters, including attendance records, assignment submission logs, platform login frequency, course interaction data, teacher observation scores, learner feedback surveys, and withdrawal records. The dataset is expected to contain around 45,000 attendance entries, 28,000 assignment records, 160,000 platform activity logs, and 3,600 teacher observation notes. Key variables include attendance decline rate, late submission frequency, login interval, feedback response time, task completion rate, peer interaction frequency, satisfaction score, and prior participation history. The study applies logistic regression, random forest, XGBoost, survival analysis, and SHAP-based model interpretation to predict high-risk learners and explain the main factors affecting participation continuity. Model performance is evaluated using AUC, F1-score, recall, precision, and early-warning lead time. The innovation of this study lies in shifting community education management from retrospective dropout analysis to early participation-risk prediction, while also introducing interpretable machine learning to help teachers understand why learners become disengaged rather than only labeling them as high-risk.
References
Huang, J., Xu, T., Yin, J., & Yang, J. (2026). Data Quality Monitoring and Intelligent Scheduling Optimization in Financial Data Workflow Automation. Available at SSRN 7179338.
Polat, S., & Bayram, H. (2026). Teacher Support as a Predictor of the Social Participation of Secondary School Students: A Hypothesis Testing Model Through the Mediating Role of Self-Confidence and Communication. Sage Open, 16(2), 21582440261457285.
Lin, T., Spivack, Z., & Chen, A. (2026). Monitoring Teaching Quality and Validating Educational Equity in Public Art Education. Available at SSRN 6512778.
Gossner, M., Dittman, C. K., Lole, L., & Miller-Lewis, L. (2025). Community insights into school disengagement: Perspectives from a regional-rural Australian context. Australian and International Journal of Rural Education, 35(2), 33-50.
Zheng, J., & Makar, M. (2022). Causally motivated multi-shortcut identification and removal. Advances in Neural Information Processing Systems, 35, 12800-12812.
Zhang, Z., Tong, Y., & Gao, Y. (2026). Causal Representation Learning for Explainable Early Warning in High-Stakes Decision Systems.
Usiobaifo, A. R., & Roseline, O. O. (2025). A Lecture Reminder System For Enhancing Student Engagement. Journal of Electrical Engineering, Electronics, Control and Computer Science, 10(2), 9-18.
Qi, C., & Qiao, X. (2026). Using AI to Monitor AI: Automated Operations Through Log-Driven Intelligence. Available at SSRN 6795840.
Su, D., & Wu, Y. (2026). Multilevel Growth and Social Network Modeling for Functional Communication Enhancement in Students with Intellectual Disabilities.
Tiznado-Aitken, I., Vecchio, G., Astroza, S., Carrasco, J. A., & Smith Piel, M. C. (2025). Profiling caregivers: caregiving workload, mobility, stress, and remote work difficulties. Urban Studies, 00420980251361626.
Shao, W. (2026, March). Interpretable Ensemble Learning for Network Traffic Anomaly Detection: A SHAP-based Explainable AI Framework for Embedded Systems Security. In 2026 14th International Symposium on Digital Forensics and Security (ISDFS) (pp. 1-4). IEEE.
Xu, T., Zhang, J., & Zhu, W. (2026). Fairness-Accuracy Trade-offs and Calibration Mechanisms in Machine Learning-Based Subprime Credit Scoring. Available at SSRN 6893759.
Arévalo-Cordovilla, F. E., & Peña, M. (2025). Evaluating ensemble models for fair and interpretable prediction in higher education using multimodal data. Scientific reports, 15(1), 29420.
Xiong, W., & Zeng, Y. (2026). Multi-Layer Coupled Diagnosis of Energy Efficiency Degradation in Complex Building MEP Systems and Identification of Optimization Boundaries. Available at SSRN 7121782.
Hong, Z., Chen, H., & Xu, T. (2026). Real-Time Capacity Risk Forecasting for Low-Latency Financial Trading Cloud Platforms. Available at SSRN 7118180.
Jianjun, Q., Isleem, H. F., Almoghayer, W. J., & Khishe, M. (2025). Predictive athlete performance modeling with machine learning and biometric data integration. Scientific Reports, 15(1), 16365.
Li, J., Zhang, Y., & Gu, Y. (2026). Chain-Hash Audit Framework with Trusted Anchoring for Tamper-Evident Evidence Lifecycle Management.
Zhang, Y., Wang, J., & Gu, W. (2026, February). Research on the Construction and Effectiveness of a Computer-Aided Systematic Training Framework for Wind Farm O&M Quality Amidst High Personnel Turnover. In Proceedings of the 2nd International Conference on Digital Management and Information Technology (pp. 647-651).
Tierney, J. F., Burdett, S., & Fisher, D. J. (2025). Practical methods for incorporating summary time-to-event data into meta-analysis: updated guidance. Systematic Reviews, 14(1), 84.
Moore, R. L., Wang, C., & Lee, S. S. (2026). Understanding MOOC dropout through learner intentions: A persona-based survival analysis. Computers & Education, 105636.
Huang, R. (2026). Less Is More: When Data Augmentation Hurts Small CNN Generalization. Journal of Computer and Communications, 14(7), 1-11.
Wu, J., Wu, D., Zhang, J., & Peng, Y. (2026). Generative AI Feedback in Junior High School Artistic Creation Evaluation. Available at SSRN 7244838.
Baglioni, C. G. (2025). Applying Action-Research to the analysis of motivation in FL learners: A case study on the translation of motivated behaviour into Italian teaching practice (Doctoral dissertation, University of Glasgow).
Zhang, Z., Wang, J., Li, Z., Wang, Y., & Zheng, J. (2025). Anncoder: A mti-agent-based code generation and optimization model. Symmetry, 17(7), 1087.
Huang, J., Yin, J., Yang, J., & Xu, T. (2026). Construction of Audit Evidence Chain and SOX Control Verification Mechanism for Transaction-level Financial Data in High Volume E-commerce Platform. Available at SSRN 7179259.
Naseer, F., & Khawaja, S. (2025). Mitigating conceptual learning gaps in mixed-ability classrooms: A learning analytics-based evaluation of AI-driven adaptive feedback for struggling learners. Applied Sciences, 15(8), 4473.
Wu, J., Zhang, J., Wu, D., & Peng, Y. (2026). Visual Transformation Mechanisms for Integrating Digital Cultural Heritage Resources into Junior High School Art Curricula.
Swiderski, T., Fuller, S. C., & Bastian, K. C. (2026). Student-level attendance patterns across three post-pandemic years. Educational Evaluation and Policy Analysis, 48(1), 400-407.
Lin, N., Xu, Y., Yang, H., Zhang, G., Zhang, M., Wang, S., ... & Li, X. (2020). Dissociating the neural correlates of the sociality and plausibility effects in simple conceptual combination. Brain Structure and Function, 225(3), 995-1008.
Mahmud, M. M., Teh, J. K. L., & Azizan, S. N. (2026, April). Hyflex learning and student engagement in higher education: a systematic literature review. In Frontiers in Education (Vol. 11, p. 1773704). Frontiers Media SA.