A Stacking Ensemble Machine Learning Framework for Predicting Academic Performance and Identifying At-Risk Students in Rural Secondary Schools: Evidence from Aurangabad District, Maharashtra

Secondary rural schools need to be able to identify at-risk students prior to the conclusion of Class 10 exams. This research project developed and tested a machine-learning approach for predicting three tasks: pass or fail, percentage scores, and the most probable subject of failure. The dataset consisted of approximately 6,000 actual student files collected by the researcher from secondary schools located within the Aurangabad district. Support for collecting the data was provided by a Zilla Parishad office letter asking for the cooperation of all the schools. The researcher retained available hard copy documentation related to this process. Each file contained 23 academic, behavioural, school, and home-related attributes. Fifteen different algorithms were evaluated and the Stacking Classifier was chosen to predict whether or not a student will pass or fail. The decision threshold for the Stacking classifier was adjusted using the F2 score to minimize the number of students who failed that the model missed. For the score prediction task, Elastic Net was chosen. Attendance and hours spent studying per day were each hypothesized as being associated with pass/fail status. Both attendance (p < .001) and study time (p < .001) were significantly different among students classified as having passed versus those who had failed. On test data, the stacking model produced an area under the ROC curve (AUC = .936), along with an 88.9% recall rate. In its subsequent implementation into CORE6, the model was constrained to use only six relatively simple variables that could be easily gathered from schools: ninth grade marks; attendance; study hours; an infrastructure quality score; level of education attained by parents; and availability of a coach. The findings demonstrate that it is possible to develop an early warning system for identifying students at risk of failing in secondary schools in rural areas based upon a limited amount of input information readily available at the school level.

prediction of student performance; machine learning; stacking ensembles; mining educational data; identifying at-risk students; attendance; hours of study; secondary education in rural areas

1. Ghalib Abdillah et al. (2025). Data-Driven Approach for Decision Making in Higher Education Institution. International Conference on Computing and Artificial Intelligence. [Google Scholar] [Crossref]

2. https://doi.org/10.1109/ICCAI65301.2025.11278967 [Google Scholar] [Crossref]

3. Samuel-Soma M. Ajibade et al. (2019). Educational Data Mining: Enhancement of Student Performance model using Ensemble Methods. IOP Conference Series: Materials Science and Engineering. https://doi.org/10.1088/1757-899X/551/1/012061 [Google Scholar] [Crossref]

4. Hemanth Reddy Alavala et al. (2025). Educational Data Mining for Predicting Academic Outcomes Using Ensemble Techniques. 2025 International Conference on Visual Analytics and Data Visualization (ICVADV). https://doi.org/10.1109/ICVADV63329.2025.10961471 [Google Scholar] [Crossref]

5. E. A. Aldhahri et al. (2025). Regularized multi-path XSENet ensembler for enhanced student performance prediction in higher education. PeerJ Computer Science. https://doi.org/10.7717/peerj-cs.3032 [Google Scholar] [Crossref]

6. Nashwa Ali & Nishat Sultana (2025). A Study on Information & Communication Technologies and Its Impact on Higher Education Institutions. Journal of Artificial Intelligence and Emerging Technologies. https://doi.org/10.47001/jaiet/2025.203002 [Google Scholar] [Crossref]

7. Elaf Abu Amrieh et al. (2016). Mining Educational Data to Predict Student’s academic Performance using Ensemble Methods. https://doi.org/10.14257/IJDTA.2016.9.8.13 [Google Scholar] [Crossref]

8. Niel Ananto (2024). Leveraging Ensemble Learning for Predicting Student Graduation: A Data Mining Approach. Prosiding Seminar Nasional Forum Manajemen Indonesia - e-ISSN 3026-4499. [Google Scholar] [Crossref]

9. https://doi.org/10.47747/snfmi.v2i1.2320 [Google Scholar] [Crossref]

10. Maxsi Ary et al. (2025). Optimizing Decision-Making in Higher Education Institutions through AI-Driven Business Intelligence in the Digital Era. International Journal of Economics, Management and Accounting. https://doi.org/10.47353/ijema.v3i3.328 [Google Scholar] [Crossref]

11. Arvind Bagale (2026). Early Warning System for Student Dropout Risk Using Behavioral Analytics, Explainable AI, and Hybrid Machine Learning Models. International Journal for Research in Applied Science and Engineering Technology. https://doi.org/10.22214/ijraset.2026.82568 [Google Scholar] [Crossref]

12. S. P. Baliyan & P. Baliyan (2018). Socio-economic Factors as Predictors of Undergraduate Students’ Attitude towards Entrepreneurship in Botswana. Journal of Entrepreneurship and Business Innovation. https://doi.org/10.5296/JEBI.V5I1.13084 [Google Scholar] [Crossref]

13. Mohamed Bellaj et al. (2024). Educational Data Mining: Employing Machine Learning Techniques and Hyperparameter Optimization to Improve Students' Academic Performance. Int. J. Online Biomed. [Google Scholar] [Crossref]

14. Eng.. https://doi.org/10.3991/ijoe.v20i03.46287 [Google Scholar] [Crossref]

15. Abdelkarim Bettahi et al. (2025). A Modular and Explainable Machine Learning Pipeline for Student Dropout Prediction in Higher Education. Algorithms. https://doi.org/10.3390/a18100662 [Google Scholar] [Crossref]

16. W. Choi et al. (2024). Analyzing the Interpretability of Machine Learning Prediction on Student Performance Using SHapley Additive exPlanations. International Conference on Teaching, Assessment, and Learning for Engineering. https://doi.org/10.1109/TALE62452.2024.10834292 [Google Scholar] [Crossref]

17. Khagen Das & S. Kalita (2025). Effectiveness of Ishan Uday Scholarship in case of Gross Enrolment Ratio and Academic Success in North-Eastern States of India. Shanlax International Journal of Arts, Science and Humanities. https://doi.org/10.34293/sijash.v13i1.9140 [Google Scholar] [Crossref]

18. Sreekala Edannur & Abdul Rasak.C (2017). INEQUALITIES OF ACCESSING HIGHER EDUCATION IN INDIA: A STUDY AMONG THE BACKWARD CLASS STUDENTS. https://www.semanticscholar.org/paper/9500b93ad1b73df94318f568b49c0e5c5c95c5bc [Google Scholar] [Crossref]

19. Micheline A. Gotardo (2019). Using Decision Tree Algorithm to Predict Student Performance. Indian Journal of Science and Technology. https://doi.org/10.17485/IJST/2019/V12I5/140987 [Google Scholar] [Crossref]

20. Sachini Gunasekara & Mirka Saarela (2025). Explainable AI in Education: Techniques and Qualitative Assessment. Applied Sciences. https://doi.org/10.3390/app15031239 [Google Scholar] [Crossref]

21. Enrique De La Hoz et al. (2026). Actionable Learning Analytics: Predicting University Performance Levels with Interpretable Machine Learning. Journal on Efficiency and Responsibility in Education and Science. https://doi.org/10.7160/eriesj.2026.190102 [Google Scholar] [Crossref]

22. J. Ishengoma (2018). The Socio-economic Background of Students Enrolled in Private Higher Education Institutions in Tanzania: Implications for Equity. [Google Scholar] [Crossref]

23. https://www.semanticscholar.org/paper/83b17c1788fd69862bca2d6a78b0683717a4851f [Google Scholar] [Crossref]

24. Li Jing et al. (2025). Development of an interpretable machine learning model for frailty risk prediction in older adult care institutions: a mixed-methods, cross-sectional study in China. BMJ Open. https://doi.org/10.1136/bmjopen-2024-095460 [Google Scholar] [Crossref]

25. J. K et al. (2025). Hybrid Random Forest and Logistic Regression Model for Predicting Student Academic Performance in Higher Education. 2025 5th Asian Conference on Innovation in Technology (ASIANCON). https://doi.org/10.1109/ASIANCON66527.2025.11280932 [Google Scholar] [Crossref]

26. Shubham Kishor Kadam et al. (2026). The Digital Divide: Challenges in Artificial Intelligence Adoption across Higher Education Institutions. Journal of Information and Communications Technology: Algorithms, Systems and Applications. https://doi.org/10.64189/ict.26304 [Google Scholar] [Crossref]

27. Khalida Khan (2022a). Choice of higher education in India and its determinants. International Journal of Economic Policy Studies. https://doi.org/10.1007/s42495-021-00077-y [Google Scholar] [Crossref]

28. Khalida Khan (2022b). The impact of caste and religious background on participation in higher education: evidence from Uttar Pradesh in India. Journal of Social and Economic Development. https://doi.org/10.1007/s40847-022-00220-1 [Google Scholar] [Crossref]

29. Rajkumar Kuppuswami et al. (2026). AI-Integrated Multi-Modal Model for Climate Hazard Assessment and Adaptation Planning. 2026 International Conference on Multidisciplinary Innovations For Smart & Sustainable Future (MISSF). https://doi.org/10.1109/MISSF68264.2026.11522083 [Google Scholar] [Crossref]

30. Gloria L Lopez-Muñoz et al. (2026). Student Dropout Prediction in Higher Education: A Systematic Review of Machine Learning Methods and Risk Factors. Journal of Information Technology Education: Research. https://doi.org/10.28945/5776 [Google Scholar] [Crossref]

31. Kajal Mahawar & Punam Rattan (2024). Empowering education: Harnessing ensemble machine learning approach and ACO-DT classifier for early student academic performance prediction. Education and Information Technologies : Official Journal of the IFIP technical committee on Education. https://doi.org/10.1007/s10639-024-12976-6 [Google Scholar] [Crossref]

32. Thomas Mgonja (2024). Using interpretable machine learning approaches to predict and provide explanations for student completion of remedial mathematics. Education and Information Technologies : Official Journal of the IFIP technical committee on Education. [Google Scholar] [Crossref]

33. https://doi.org/10.1007/s10639-024-12647-6 [Google Scholar] [Crossref]

34. Nazyrova et al. (2025). The Digital Transformation of Higher Education in the Context of an AI-Driven Future. Sustainability. https://doi.org/10.3390/su17229927 [Google Scholar] [Crossref]

35. Melaka Pathiranagama et al. (2025). Beyond the Black Box: An Interpretable Machine Learning Approach to Student Dropout Prediction. International Conference on Automation and Computing. https://doi.org/10.1109/ICAC69156.2025.11361534 [Google Scholar] [Crossref]

36. G. Pavan et al. (2025). Data-Driven Insights for Academic Success: Predicting Student Performance Using Machine Learning. International Journal of Advanced Scientific Research and Engineering Trends. https://doi.org/10.65521/ijasret.v9i3.1841 [Google Scholar] [Crossref]

37. G. Prakasam et al. (2019). Enrolment by academic discipline in higher education: differential and determinants. https://doi.org/10.1108/JABES-12-2018-0104 [Google Scholar] [Crossref]

38. S. Pramanik (2015). The Effect of Family Characteristics on Higher Education Attendance in India. https://doi.org/10.1177/2347631114558190 [Google Scholar] [Crossref]

39. Riyadi Purwanto et al. (2025). A Comparative Analysis of KIP-K Acceptance Prediction Based on School Type Using XGBoost, Random Forest, and SVM-RBF: Evaluation Through Accuracy and Data Visualization. Journal of Innovation Information Technology and Application (JINITA). [Google Scholar] [Crossref]

40. https://doi.org/10.35970/10.35970/jinita.v7i2.2948 [Google Scholar] [Crossref]

41. Mardi Yudhi Putra et al. (2025). Hybrid Voting Ensemble of Logistic Regression, Random Forest, KNN, SVM, and XGBoost for Student Drop Out Prediction. International Conference on Intelligent Computing. https://doi.org/10.1109/ICIC68054.2025.11309379 [Google Scholar] [Crossref]

42. George Raftopoulos et al. (2024). Fair and Transparent Student Admission Prediction Using Machine Learning Models. Algorithms. https://doi.org/10.3390/a17120572 [Google Scholar] [Crossref]

43. Andi Dwi Riyanto et al. (2025). Identifying Key Factors Influencing Student Satisfaction Using Explainable AI and Shapley Additive Explanations for Predictive Modeling. 2025 9th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE). https://doi.org/10.1109/ICITISEE68184.2025.11355001 [Google Scholar] [Crossref]

44. Rohit et al. (2026). Socio-Economic and Personal Profiles of Agriculture Graduates in India: Implications for Professional Pathways. Archives of Current Research International. [Google Scholar] [Crossref]

45. https://doi.org/10.9734/acri/2026/v26i31772 [Google Scholar] [Crossref]

46. Azqa Saleem et al. (2025). Using Stack Modelling Technique for Student Performance Prediction: An Educational Data Mining Approach. IPSI Transactions on Internet Research. [Google Scholar] [Crossref]

47. https://doi.org/10.58245/ipsi.tir.2501.05 [Google Scholar] [Crossref]

48. M. Sethy & Sandhya R. Mahapatro (2025). NEP 2020 and Indian Higher Education: Pathways to Holistic, Flexible, and Global Transformation. Journal of International Education and Practice. https://doi.org/10.30564/jiep.v8i1.11607 [Google Scholar] [Crossref]

49. Alba Catalina Morales Tirado et al. (2024). Towards an Operational Responsible AI Framework for Learning Analytics in Higher Education. arXiv.org. https://doi.org/10.48550/arXiv.2410.05827 [Google Scholar] [Crossref]

50. Srinivas Venu (2026). AI Literacy in Higher Education and India's Strategic Vision Viksit Bharat 2047. International journal of professional studies. https://doi.org/10.37648/ijps.v21i03.004 [Google Scholar] [Crossref]

51. N. Vo et al. (2026). Artificial Intelligence-Driven Early Prediction of Student Dropout and Academic Outcomes in Higher Education: A Comparative Study of Advanced Machine Learning Approaches. EAI Endorsed Transactions on Industrial Networks and Intelligent Systems. [Google Scholar] [Crossref]

52. https://doi.org/10.4108/eetinis.131.11758 [Google Scholar] [Crossref]

53. C. Walsh (2026). Student Success and Predictive Learner Analytics in Higher Education: Navigating the Ethics of Transparency. HCAIep. https://doi.org/10.1145/3777490.3779128 [Google Scholar] [Crossref]

54. W. Yousef et al. (2025). Enhancing University Admissions through Scalable and Fair Machine Learning Models: A Case Study from Yemeni Universities. 2025 5th International Conference on Emerging Smart Technologies and Applications (eSmarTA). [Google Scholar] [Crossref]

55. https://doi.org/10.1109/eSmarTA66764.2025.11132267 [Google Scholar] [Crossref]

56. Zhifeng Zhang et al. (2025). A Multi-Branch Convolutional Neural Network for Student Graduation Prediction. Algorithms. https://doi.org/10.3390/a18110711 [Google Scholar] [Crossref]

57. Khrystyna Zub et al. (2023). Two-Stage PNN-SVM Ensemble for Higher Education Admission Prediction. Big Data and Cognitive Computing. https://doi.org/10.3390/bdcc7020083 [Google Scholar] [Crossref]

• Classifying News Articles on Nigerian Newspapers Using Machine Learning
• Approaching Early Dyslexia Prediction with Ensemble Machine Learning: A Secondary Empirical Analysis of the Rello Et Al. Public Behavioural Dataset
• Machine Learning Modelling of Geostationary SBAS Satellite Orbit Errors Observed from an Equatorial West African Station
• A Comparative Study of CNN and Vision Transformer Models in Alzheimer's Detection
• Hybrid Ensemble Learning For Malicious URL Detection: A Literature Review of Machine Learning, Deep Learning, and Feature-Fusion Approaches