Analysis of Students Stress Level using Machine Learning Algorithms

Prevalence of stress among the student population constitutes a significant concern that impinges upon their academic performance and overall psychological well-being. This research endeavour is centered on the examination of student stress levels through the application of machine learning methodologies. The dataset encompasses variables including student academic and personal details along with Stress levels which are classified into three distinct categories: low, moderate, and high, predicated on these various factors. The machine learning models employed in this study include Support Vector Machines (SVM), and Decision Trees, Artificial Neural Networks (ANN), Ada Boosting each chosen for their capacity to discern patterns and correlations within the dataset. Decision Tree is particularly adept at capturing intricate relationships and yields a high degree of accuracy. The results underscore that the number of study hours, duration of sleep, and GPA emerge as the most significant influences in predicting the stress level of students.