A Comparative Analysis of Stress Level in Men and Women Through Machine Learning Classifier

A fast growing area of research has been the investigation of the levels of stress between men and women by classification algorithms, especially in the regard to mental health and its implications regarding quality of life. This research summarizes a finding which utilizes machine learning techniques like decision tree, support vector machine, random forest, naïve bayes and k-nearest neighbor are used to predict stress levels based on physiological signals. Our aim is to identify gender-specific stress patterns, determine key predictors, and develop classification models to enhance our understanding of stress across genders. We used a comprehensive, publicly available dataset that comprises stress-related information from a balanced sample of men and women, including standardized stress questionnaires, physiological measurements, and demographic information. In this research Random Forest Tress gives the most appropriate result by achieving an accuracy of 100%.