Rupali Jadhav,
Piyush Girase,
- PhD scholar, Department of Master of Computer Science, Atmiya University Rajkot, Gujarat, India
- Software engineer, Department of Computer Science, Cognizant Technology Solutions, Tamil Nadu, India
Abstract
Most contemporary digital learning environments encounter persistent challenges when it comes to accurately identifying students who are at-risk of academic underperformance. These challenges often arise due to limited visibility in learners’ engagement levels and gaps in conceptual understanding, particularly during the early stages of a course. To address this issue, the present study proposes an early prediction framework that leverages comprehensive student-related data through the application of machine learning techniques. The framework aims to detect at-risk students before their performance significantly declines, enabling timely interventions. In this research, five classification algorithms: random forest, logistic regression, support vector machine (SVM), and K-nearest neighbors (KNN) were trained using a student performance dataset. The models were evaluated using standard performance metrics, including accuracy, precision, recall, and F1-score, to ensure a balanced and reliable comparison. Among all the tested approaches, tree-based ensemble methods, particularly the random forest classifier, demonstrated superior predictive performance across most evaluation criteria. This highlights the effectiveness of ensemble learning in capturing complex patterns within educational data. The findings suggest that integrating learning analytics with machine learning techniques can significantly enhance the early identification of academically vulnerable students. Such predictive systems can support educators by enabling timely academic assistance, personalized learning strategies, and targeted resource allocation. Despite certain limitations, such as dataset size and class imbalance, the study underscores the strong potential of data-driven approaches to minimize learning gaps and promote improved student outcomes in real-world educational settings.
Keywords: Academic risk detection, at-risk student performance, classification models, learning analytics, machine learning, predictive modeling, random forest
[This article belongs to International Journal of Algorithms Design and Analysis Review ]
Rupali Jadhav, Piyush Girase. Predictive Analytics and Adaptive Learning: A Machine Learning Framework for Reducing Learning Gaps. International Journal of Algorithms Design and Analysis Review. 2026; 04(01):16-21.
Rupali Jadhav, Piyush Girase. Predictive Analytics and Adaptive Learning: A Machine Learning Framework for Reducing Learning Gaps. International Journal of Algorithms Design and Analysis Review. 2026; 04(01):16-21. Available from: https://journals.stmjournals.com/ijadar/article=2026/view=241136
References
- Alkan BB, Kuzucuk S, Alkan N, Sinan A. Using machine learning to predict student outcomes for early intervention and formative assessment. Sci Rep. 2025;15(1):39797. doi:10.1038/s41598-025-23409-w. PMID: 41233395.
- Nimy E, Mosia M, Chibaya C. Identifying at-risk students for early intervention: A probabilistic machine learning approach. Appl Sci. 2023;13(6):3869. doi:10.3390/app13063869.
- Goren O, Cohen L, Rubinstein A. Early prediction of student dropout in higher education using machine learning models. In: Demmans Epp C, Paaßen B, Joyner D, editors. Proceedings of the 17th International Conference on Educational Data Mining (EDM 2024), Atlanta, GA, USA, 2024. p. 349–359. doi:10.5281/zenodo.12729834.
- Rebelo Marcolino M, Reis Porto T, Thompsen Primo T, Targino R, Ramos V, Marques Queiroga E, et al. Student dropout prediction through machine learning optimization: Insights from Moodle log data. Sci Rep. 2025;15:9840. doi:10.1038/s41598-025-93918-1. PMID: 40119104.
- Ujkani B, Minkovska D, Hinov N. Course success prediction and early identification of at-risk students using explainable artificial intelligence. Electronics. 2024;13(21):4157. doi:10.3390/electronics13214157.
- George EB, Senthilkumar R, Al-Junaibi F, Al-Shuaibi Z. Explainable AI methods for
predicting student grades and improving academic success. J Inf Syst Eng Manag. 2025;10(23s):117–126. - Bala B, Behal S. A brief survey of data preprocessing in machine learning and deep
learning techniques. In: 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC); 2024. p. 1755–1762. doi:10.1109/I-SMAC61858.2024.10714767. - Cerqueira V, Moniz N, Soares C. VEST: Automatic feature engineering for forecasting. Mach Learn. 2024;113(7):4523–4545. doi:10.1007/s10994-021-05959-y.
- Dey D, Haque MS, Islam MM, Aishi UI, Shammy SS, Mayen MSA, et al. The proper application of logistic regression model in complex survey data: A systematic review. BMC Med Res Methodol. 2025;25(1):15. doi:10.1186/s12874-024-02454-5. PMID: 39844030.
- Hoque R, Billah M, Debnath A, Hossain SS, Sharif NB. Heart disease prediction using SVM. Int J Sci Res Arch. 2024;11(2):412–420. doi:10.30574/ijsra.2024.11.2.0435.
- Salman HA, Kalakech A, Steiti A. Random forest algorithm overview. Babylonian J Mach Learn. 2024;2024:69–79. doi:10.58496/BJML/2024/007.
- Sathyanarayanan S, Tantri BR. Confusion matrix-based performance evaluation metrics. Afr J Biomed Res. 2024;27(4):4023–4031. doi:10.53555/AJBR.v27i4S.4345.
- Erbani J, Portier PÉ, Egyed-Zsigmond E, Nurbakova D. Confusion matrices: A unified theory. IEEE Access. 2024;12:181372–181419. doi:10.1109/ACCESS.2024.3507199.
- Roumeliotis S, Schurgers J, Tsalikakis DG, D’Arrigo G, Gori M, Pitino A, et al. ROC curve analysis: A useful statistic multi-tool in the research of nephrology. Int Urol Nephrol. 2024;56(8):2651–2658. doi:10.1007/s11255-024-04022-8. PMID: 38530584.
International Journal of Algorithms Design and Analysis Review
| Volume | 04 |
| Issue | 01 |
| Received | 22/12/2025 |
| Accepted | 06/01/2026 |
| Published | 27/04/2026 |
| Publication Time | 126 Days |
Login
PlumX Metrics