Beyond Marks: Detecting Hidden Academic Risk Through Psychosocial Proxy Indicators, Machine Learning and Explainable AI in Sri Lankan Government Secondary Schools

Background: Academic monitoring in Sri Lankan government secondary schools relies exclusively on term marks, leaving the psychosocial conditions that accumulate into failure entirely invisible. No validated, explainable early warning system exists for this context, and global early warning systems depend on Learning Management System infrastructure unavailable in Sri Lankan government schools. Methods: A 24-item psychosocial questionnaire spanning five theoretically grounded domains — Socioeconomic Burden, Cognitive Load, School Environment, Motivation, and Physical Readiness — was developed through five months of structured field engagement with 12 school principals and 45 classroom teachers, validated by the Professional Psychological Counselors Association of Sri Lanka (PPCA), and approved through three institutional levels. Combined with six-term academic trajectory data from 873 Grade 11 students across 11 government schools in Piliyandala Educational Zone, eight interpretable features were engineered. Four candidate models were evaluated using 10-fold stratified cross-validation; logistic regression was selected. SHAP (SHapley Additive exPlanations) LinearExplainer was applied to produce exact, student-level risk explanations. Results: The full model achieved CV AUC=0.878 (95% CI: 0.858–0.899), a validated 6.1-point gain over the academic-only baseline (AUC=0.818), confirming independent psychosocial contribution. Failure rates rose monotonically from 7.1% to 58.2% across the psychosocial burden spectrum. SHAP analysis identified Cognitive Load and Motivation as the primary actionable risk drivers beyond marks. Critically, 219 students (25.1%) carrying above-median psychosocial burden while currently passing were identified as entirely invisible to conventional marks-only monitoring. Gender fairness evaluation confirmed equitable model performance across four independent statistical tests. Conclusion: The resulting EduRisk prototype delivers SHAP-grounded, student-level risk profiles covering the psychosocial dimensions that marks-only monitoring structurally cannot detect, providing teachers and school authorities with actionable intelligence to intervene before psychosocial burden accumulates into irreversible academic failure. The methodology offers a replicable framework for resource-constrained educational contexts globally.

Academic risk prediction, Early warning system, Explainable artificial intelligence, Psychosocial indicators, Educational equity

1. Berens, J., Schneider, K., Görtz, S., Oster, S., & Burghoff, J. (2019). Early detection of students at risk — predicting student dropouts using administrative student data and machine learning methods. Administrative Sciences, 9(2), 1–41. https://doi.org/10.3390/admsci9020042. [Google Scholar] [Crossref]

2. Choi, W. C., Lam, C. T., Pang, P. C., & Mendes, A. J. (2025). A systematic literature review of explainable artificial intelligence (XAI) for interpreting student performance prediction in computer science and STEM education. Proceedings of the ACM. https://doi.org/10.1145/3724363.3729027 [Google Scholar] [Crossref]

3. Dai, W., Lin, J., Jin, F., Tsai, Y., Srivastava, N., Le Bodic, P., Gasevic, D., & Chen, G. (2025). Learning analytics for early identification of at-risk students and feedback intervention. Journal of Learning Analytics, 12(1). https://doi.org/10.18608/jla.2025.8735 [Google Scholar] [Crossref]

4. Dayasiri, K., Jayasingha, D., & Thadchanamoorthy, V. (2025). Determinants of school drop-out among adolescents in rural Sri Lanka. Children and Youth Services Review, 169. https://doi.org/10.1016/j.childyouth.2024.108112 [Google Scholar] [Crossref]

5. Fabrigar, L. R., Wegener, D. T., MacCallum, R. C., & Strahan, E. J. (1999). Evaluating the use of exploratory factor analysis in psychological research. Psychological Methods, 4(3), 272–299. [Google Scholar] [Crossref]

6. Fornell, C., & Larcker, D. F. (1981). Evaluating structural equation models with unobservable variables and measurement error. Journal of Marketing Research, 18(1), 39–50. [Google Scholar] [Crossref]

7. Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2010). Multivariate Data Analysis (7th ed.). Pearson. [Google Scholar] [Crossref]

8. Harrell, F. E. (2015). Regression Modeling Strategies (2nd ed.). Springer. [Google Scholar] [Crossref]

9. He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263–1284. [Google Scholar] [Crossref]

10. Karalar, H., Kapucu, C., & Gürüler, H. (2021). Predicting students at risk of academic failure using ensemble model in distance learning. Education and Information Technologies, 26(4), 4031–4041. [Google Scholar] [Crossref]

11. Kotsiantis, S. B., Pierrakeas, C., & Pintelas, P. (2004). Predicting student performance in distance learning using machine learning techniques. Applied Artificial Intelligence, 18(5), 411–426. [Google Scholar] [Crossref]

12. Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774. [Google Scholar] [Crossref]

13. Macfadyen, L. P., & Dawson, S. (2010). Mining LMS data to develop an early warning system for educators: A proof of concept. Computers and Education, 54(2), 588–599. [Google Scholar] [Crossref]

14. Mudunna, C., Perera, S., & Rajapakshe, A. (2025). Prevalence and determinants of mental health problems experienced by school-going adolescents in Sri Lanka. Global Mental Health, 12, e55. [Google Scholar] [Crossref]

15. Peduzzi, P., Concato, J., Kemper, E., Holford, T. R., & Feinstein, A. R. (1996). A simulation study of the number of events per variable in logistic regression analysis. Journal of Clinical Epidemiology, 49(12), 1373–1379. [Google Scholar] [Crossref]

16. Rumberger, R. W. (2011). Dropping Out. Harvard University Press. [Google Scholar] [Crossref]

17. Trakunphutthirak, R., & Lee, V. C. S. (2022). Application of educational data mining approach for student academic performance prediction using progressive temporal data. Journal of Educational Computing Research, 60(2), 408–447. [Google Scholar] [Crossref]

18. UNESCO. (2021). Situation analysis on the effects of and responses to COVID-19 on the education sector in Asia: Sri Lanka case study. Paris: UNESCO. [Google Scholar] [Crossref]

19. Vinas-Forcade, J., Mels, C., Van Houtte, M., Valcke, M., & Derluyn, I. (2021). Can failure be prevented? Using longitudinal data to identify at-risk students upon entering secondary school. British Educational Research Journal, 47(1), 205–225. https://doi.org/10.1002/berj.3683 [Google Scholar] [Crossref]

20. Zhang, S., Li, Y., Chen, X., Liu, Y., & Wang, H. (2025). A systematic review of learning management system-based early warning systems in higher education 2012–2024. Computers and Education: Artificial Intelligence, 8. https://doi.org/10.1016/j.caeai.2025.100345 [Google Scholar] [Crossref]

• Assessment of the Role of Artificial Intelligence in Repositioning TVET for Economic Development in Nigeria
• Teachers’ Use of Assure Model Instructional Design on Learners’ Problem Solving Efficacy in Secondary Schools in Bungoma County, Kenya
• “E-Booksan Ang Kaalaman”: Development, Validation, and Utilization of Electronic Book in Academic Performance of Grade 9 Students in Social Studies
• Analyzing EFL University Students’ Academic Speaking Skills Through Self-Recorded Video Presentation
• Major Findings of The Study on Total Quality Management in Teachers’ Education Institutions (TEIs) In Assam – An Evaluative Study