Paper Contents
Abstract
Employee stress is a growing concern in modern workplaces, affecting productivity, job satisfaction, and overall mental health. Traditional methods for detecting stress often rely on post-event assessments, which may not be timely enough to prevent adverse outcomes. This research explores the application of machine learning algorithms to proactively predict employees under stress for early intervention. By analyzing key indicators such as workload, work hours, role ambiguity, and demographic attributes, machine learning models can detect patterns linked to high stress levels. The study develops predictive models using Support Vector Machines (SVM) and Extreme Gradient Boosting (XGBoost) on a synthesized dataset of employee attributes. The models demonstrate promising accuracy, enabling organizations to identify at-risk individuals and implement preventive measures such as counseling, job redesign, or flexible scheduling. The results suggest that integrating machine learning into employee wellness programs can greatly enhance organizational resilience and foster a healthier, more supportive work environment.
Copyright
Copyright © 2025 K.Ramalakshmi. This is an open access article distributed under the Creative Commons Attribution License.
