AI-Powered Student Mental Health Analytics and Academic Prediction System: A Supervised Machine Learning and Explainable AI Approach

Abstract

Student mental health difficulties such as stress, anxiety, depression and poor sleep frequently go unnoticed until they have already affected attendance, grades and personal wellbeing, because traditional counselling depends on a student voluntarily seeking help. This paper presents an AI-Powered Student Mental Health Analytics and Early Intervention System, a role-based web platform that combines validated psychological screening instruments — the PHQ-9, GAD-7 and Perceived Stress Scale (PSS) — with academic and lifestyle indicators such as CGPA, attendance, sleep duration, exercise and social support to build a comprehensive student risk profile. Collected data is cleaned and engineered before being passed through an ensemble of supervised learning models — Random Forest, Gradient Boosting, XGBoost and a Voting Classifier — which jointly classify each student's mental health status as Low, Moderate or High Risk and estimate likely academic performance. SHAP (SHapley Additive exPlanations) is applied so that every prediction is interpretable to the counsellors who act on it. The system is implemented with Django and Python on the backend, MySQL for persistence, and HTML/CSS/Bootstrap/JavaScript with Chart.js on the frontend, and provides three dedicated modules — Student, Counselor and Administrator — each with role-specific dashboards, along with dedicated reporting, analytics, notification and security modules. High-risk classifications trigger automatic counsellor alerts, while an institution-wide analytics dashboard surfaces department- and cohort-level trends. Functional testing across authentication, assessment, prediction, reporting, analytics, counselling and notification confirmed correct end-to-end operation, and the ensemble classifier achieved strong performance on accuracy, precision, recall and F1-score. The system demonstrates that combining validated clinical screening tools with explainable ensemble learning can support proactive, scalable and transparent early intervention in educational institutions.