International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Machine Learning Techniques for Student Performance Prediction: A Multi-Institution Study with Deployment Simulation |
|---|---|
| ABSTRACT | Universities can improve student outcomes by flagging at-risk students early. This study compares seven supervised learning algorithms—Decision Tree, Random Forest, SVM, Naïve Bayes, XGBoost, LightGBM, and MLP—on survey-derived academic, behavioral, and demographic features from 342 students at CMR University (training) and 78 at Jain University (external validation). Under 10-fold cross-validation, XGBoost achieved the highest accuracy (93.2% ± 1.8%, F1 = 0.92), ahead of Random Forest (91.7%) and LightGBM (92.5%), and retained 90.1% accuracy on the external Jain dataset. Attendance (0.31), assignment consistency (0.27), and self-reported stress (0.19) were the dominant predictors. Learning-curve and precision-recall analyses confirmed strong generalization and minority-class (fail) performance (AP = 0.89). A deployment simulation correctly flagged 78% of at-risk students by week six, supporting the practical viability of data-driven early-warning systems. |
| AUTHOR | DR. DEEPA A, AKHILA S BABU, ANUSHA H V, KAVYA M ACHARI, AISHWARYA S K School of Science and Computer Studies, CMR University, Bangalore, India |
| VOLUME | 188 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1409013 |
| pdf/13_Machine Learning Techniques for Student Performance Prediction A Multi-Institution Study with Deployment Simulation.pdf | |
| KEYWORDS | |
| References |
[1] S. K. Sharma, P. K. Sinha, and M. T. Rahman, "Digital transformation in higher education: A 2025 perspective," IEEE Trans. Educ., vol. 68, no. 1, pp. 45–59, 2025. [2] H. Aldowah, H. Al-Samarraie, and W. M. Fauzy, "Educational data mining and learning analytics: A review," IEEE Access, vol. 11, pp. 12034–12056, 2023. [3] R. S. Baker and P. S. Inventado, "Educational data mining and learning analytics," in Handbook of Learning Analytics, 2nd ed., SoLAR, 2024, pp. 89–104. [4] O. H. T. Lu et al., "Transfer learning for cross-institutional student performance prediction," IEEE Trans. Learn. Technol., vol. 15, no. 4, pp. 456–469, 2022. [5] A. M. Shahiri, W. Husain, and N. A. Rashid, "A review on predicting student's performance using data mining," Procedia Comput. Sci., vol. 72, pp. 414–422, 2015. [6] P. Cortez and A. Silva, "Using data mining to predict secondary school student performance," in Proc. FUBUTEC, 2008, pp. 5–12. [7] H. Waheed et al., "Predicting academic performance of students from VLE big data using deep learning," Comput. Hum. Behav., vol. 104, 2020. [8] E. Alyahyan and D. Düştegör, "Predicting academic success in higher education: Literature review," Int. J. Educ. Technol. High. Educ., vol. 17, 2020. [9] N. Sghir, A. Adadi, and M. Lahmer, "Recent advances in predictive learning analytics," IEEE Trans. Learn. Technol., vol. 16, no. 4, pp. 512–530, 2023. [10] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. ACM SIGKDD, 2016, pp. 785–794. [11] G. Ke et al., "LightGBM: A highly efficient gradient boosting decision tree," in NeurIPS, vol. 30, 2017. [12] M. A. Hussain, S. H. Ahmed, and K. R. Ahmed, "A comprehensive feature set for student performance prediction," J. Educ. Data Mining, vol. 15, no. 2, 2024. [13] L. Chen and T. Watanabe, "Psychological factors in educational data mining: A meta-analysis," Comput. Educ., vol. 198, 2024. [14] S. Bhattacharya and P. K. Sinha, "The paradox of online learning in Indian higher education," IEEE Trans. Educ., vol. 67, no. 3, 2024. [15] F. Pedregosa et al., "Scikit-learn: Machine learning in Python," J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011. [16] L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001. [17] C. Cortes and V. Vapnik, "Support-vector networks," Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995. [18] J. R. Quinlan, "Induction of decision trees," Mach. Learn., vol. 1, no. 1, pp. 81–106, 1986. [19] D. R. R. Penha, A. C. L. F. Carvalho, and D. F. Oliveira, "Educational data mining for student performance prediction: A review," IEEE RITA, vol. 20, no. 1, 2025. [20] M. S. Khan, S. R. Hussain, and T. A. Alghamdi, "Deep learning for early warning systems in higher education," IEEE Trans. Artif. Intell., vol. 5, no. 2, 2024. |
