A Dual Model for Predicting Student Dropout Risks and a Future-Oriented Career Guidance System using Machine Learning

The Student Success and Career Navigation Management System provides a comprehensive solution for addressing two critical challenges in education: student dropout prevention and career guidance. By integrating machine learning-based dropout prediction, psychometric assessment, career recommendation generation, and intervention management within a single platform, the system enables educational institutions to identify at-risk students at an early stage and take proactive measures to support their academic success.   The proposed system leverages data-driven techniques to improve decision-making for educators while helping students gain a better understanding of their interests, strengths, and future career opportunities. The implementation demonstrates the effective use of modern technologies such as Streamlit, Python, SQLite, SQLAlchemy, and Scikit-learn in developing an intelligent educational support system. Overall, the system contributes toward improving student retention, enhancing career awareness, and promoting a more personalized and supportive learning environment.

1.      Marcolino, M.R., et al.: Student Dropout Prediction through Machine Learning Methodologies. Scientific Reports, Nature (2025). 2.      Zhang, H., Miller, J., Weber, D.: Predicting Student Dropout Risk Through Machine Learning Analysis of Behavioral Patterns. International Journal of Engineering and Computer Science, 14(11) (2025). 3.      Nandi, S., et al.: Sankalp: AI-Powered Career Guidance System. IEEE Conference Proceedings (2025). 4.      Ajayi, O.O.: Predicting Student Dropout Risk in Online Learning using Stacked Ensemble Machine Learning and Explainable AI Techniques. International Journal of Computer Applications, 187(40) (2025). 5.      Zaidi, S.: AI-Powered Career Coach: A Review on Digital Career Guidance Systems. AIJR Proceedings (2025). 6.      Radić, G., Jovanović, L., Bacanin, N., Živković, M.: Identifying and Understanding Student Dropouts Using Metaheuristic-Optimized Classifiers and Explainable AI Techniques. ResearchGate (2024). 7.      Zapata-Medina, D., et al.: Improving Automatic Detection of Dropout Risk in Middle and High School Students. ResearchGate (2024). 8.      Ghuge, M., Kumari, A., Kamble, T., Raikwar, V.: Envisioning Tomorrow: AI Powered Career Counseling. IEEE, ResearchGate (2024). 9.      Kumari, A., et al.: AI-Powered Career Counseling Framework Integrating Large Language Models and Labor Market Trends. (2024). 10.   Birajdar, A., Jadhav, S., Shinde, P., Shinde, S., Inamdar, I.Y., Pandhare, S.D.: AI-Powered Career Counselling. International Research Journal of Engineering and Technology (IRJET) (2024).