Proactive Student Wellbeing Monitoring in K-12 Schools Using Machine Learning

This study presents WellScan, a machine learning-driven framework aimed at proactively identifying and addressing student wellbeing concerns in K-12 schools. By integrating psychological and educational models such as Maslow's Hierarchy of Needs and Seligman's PERMA framework, the system evaluates student wellbeing through a multi-dimensional analysis of physical, emotional, and environmental factors. Utilizing Random Forest and Gradient Boosting algorithms, the model predicts students at risk of wellbeing challenges, facilitating timely interventions before issues escalate. A pilot study with 400 students demonstrated a strong correlation between higher wellbeing scores and improved academic performance. This research not only underscores the value of predictive analytics in education but also highlights critical ethical considerations in the implementation of AI-driven student support systems. This research highlights the role of predictive modelling in reshaping school wellbeing strategies, offering a scalable, datadriven approach that can be integrated into global education systems.