MENTAL HEALTH PREDICTION IN STUDENTS USING MACHINE LEARNING TECHNIQUES

Abstract

In recent years, students have faced more stress because of heavy studies, lifestyle changes, and social pressure. These issues have made mental health problems worse, showing the need for early help and proper support. This project builds a machine learning model to predict student’s mental health using different factors such as age, gender, study time, grades, sleep, exercise, and emotional balance. At first, unsupervised learning methods like K-Means and Gaussian Mixture Models were used to group students based on their mental health risk levels. These groups were then used to train supervised models such as Random Forest and Logistic Regression to make accurate predictions. The model gave strong results in finding students who might need mental health support. This study shows how Machine Learning technique can help schools and colleges take early action to protect and improve student’s well-being. Counsellors and educators can use the system's predictions to help them identify students who are at risk and provide timely interventions. All things considered, this study shows how data science and psychology can be combined to develop proactive strategies for fostering mental wellness in educational settings.