AI-DRIVEN STUDENT PROFILING FOR DROPOUT, EMPLOYABILITY, AND CAREER PATH PREDICTION VIA HYBRID MODELING
DOI:
https://doi.org/10.63503/c.acset.2025.1Keywords:
Educational Data Mining (EDM), Outcome-Based Education (OBE), Student Employability, Classification Algorithms, Rubric-Based Evaluation, K-Means Clustering, Machine Learning, Holistic Assessment, Dropout Prediction, Industry ReadinessAbstract
In the era of Outcome-Based Education (OBE) and employability-driven learning, educational institutions face increasing pressure to assess student readiness beyond academic performance. This study presents a hybrid machine learning framework that integrates rubric-based scoring, supervised classification, and unsupervised clustering to predict holistic student outcomes. A comprehensive dataset of 1500 undergraduate students (2015–2025) from Tamil Nadu, India, was used, encompassing academic scores, aptitude results, behavioral traits, communication skills, leadership qualities, and employability indicators. Six classifiers—Decision Stump, Hoeffding Tree, J48, LMT, Random Tree, and RepTree—were evaluated using 10-fold cross-validation. J48 achieved the highest accuracy of 99.1%, followed by LMT and RepTree. Additionally, K-Means clustering was employed to uncover natural groupings of students into four categories: Industry-Ready, Higher Studies Aspirants, Dropout Risk, and Entrepreneurial Potential. The proposed hybrid model enhances prediction accuracy, supports early interventions, and provides actionable insights for institutional decision-making. This work aligns with national education policies and global employability standards, offering a scalable framework for data-driven student evaluation and career readiness planning.
References
1. Zhou, M., Hu, H., and Wang, C. A hybrid deep learning approach for student performance prediction. IEEE Access, 2023. 11: p. 20104–20116. DOI: 10.1109/ACCESS.2023.3245030.
2. Kumar, P., and Karthikeyan, R. Adaptive learning analytics using AI for higher education in India. Journal of Learning Analytics and Educational Data Science, 2022. 7(2): p. 22–31.
3. Albreiki, B., Zemerly, M. J., and Almuhrzi, H. Employability prediction using machine learning techniques. Education and Information Technologies, 2021. 26(3): p. 3113–3135. DOI: 10.1007/s10639-020-10400-7.
4. Al-Rahmi, W. M., Yahaya, N., Alamri, M. M., and Aljarboa, N. A. Predicting academic performance and dropout with machine learning: A case study. Computers & Education, 2021. 173(1): p. 104271. DOI: 10.1016/j.compedu.2021.104271.
5. Ministry of Human Resource Development. National Education Policy (NEP) 2020. 2020, New Delhi: Government of India. [Online]. Available: https://www.education.gov.in
6. Kukreja, R., Rani, R., and Dhand, A. Student performance prediction using hybrid model of data mining techniques. Procedia Computer Science, 2020. 167: p. 2554–2560. DOI: 10.1016/j.procs.2020.03.316.
7. Wolff, A., Zdrahal, Z., Nikolov, A., and Pantucek, M. Predicting student performance from LMS data using machine learning: A case study from Open University UK. Computers in Human Behavior, 2020. 92: p. 486–497. DOI: 10.1016/j.chb.2018.11.012.
8. García, J. A., García-Sánchez, P., and García, M. An intelligent system for evaluating the employability of university graduates. Expert Systems with Applications, 2016. 46: p. 260–273. DOI: 10.1016/j.eswa.2015.10.037.
9. UNESCO. Education 2030: Incheon Declaration and Framework for Action for the Implementation of Sustainable Development Goal 4. 2015, Paris: UNESCO. [Online]. Available: https://unesdoc.unesco.org
10. Shahiri, A. M., Husain, W., and Rashid, N. A. A review on predicting student’s performance using data mining techniques. Procedia Computer Science, 2015. 72: p. 414–422. DOI: 10.1016/j.procs.2015.12.157.
11. Yadav, S. K., Bharadwaj, B., and Pal, S. Data mining applications: A comparative study for predicting student’s performance. International Journal of Innovative Technology and Creative Engineering, 2012. 1(12): p. 13–19.
12. Sembiring, S., Zarlis, M., Hartama, D., Ramliana, and Wani, E. Prediction of student academic performance using decision tree and Bayes classification on Moodle data. International Journal of Information and Education Technology, 2011. 1(2): p. 110–116.
13. Bhardwaj, B. K., and Pal, S. Data mining: A prediction for performance improvement using classification. International Journal of Computer Science and Information Security (IJCSIS), 2011. 9(4): p. 136–140.
14. Romero, C., and Ventura, S. Educational data mining: A review of the state of the art. IEEE Transactions on Systems, Man, and Cybernetics – Part C, 2010. 40(6): p. 601–618. DOI: 10.1109/TSMCC.2010.2053532.
15. Baker, R. S. J. d., and Yacef, K. The state of educational data mining in 2009: A review and future visions. Journal of Educational Data Mining, 2009. 1(1): p. 3–17.
16. Kumar, V., and N. A. Long-term effects of AI-personalized learning on engagement and performance. International Journal of Environmental Sciences, 2025. p. 1601–1608.
17. Vijaya Kumar, K., and Naveen, A. AI-driven student performance prediction using multi-class classifiers. International Journal of Innovative Science and Research Technology, 2025. 10(9): p. 2639–2645. DOI: 10.38124/ijisrt/25sep1354.
18. Krishnan, V., and N. A. A data-driven framework for holistic student performance evaluation and industry readiness using machine learning. IRE Journals, 2024. 9(3).
