Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202997,
        author = {Vaishnavi Gamit},
        title = {Stress Level Estimation in Working Professionals},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {10708-10723},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202997},
        abstract = {Job stress has become one of the major challenges of professional life in the modern age and it impacts the mental well-being, job output and general living. This paper, Data-Driven Stress Assessment for Professionals, aims to look at different aspects of stress including lifestyle habits, working patterns and routines with the use of machine learning to determine how the above factors affect stress. It contains the data of 50000 subjects with 17 variables ranging over demographics (age, gender, country and occupation), work-life balance measures (working hours, sleep duration and physical activity), and lifestyle-based choices (diet quality, smoking, alcohol consumption and social media consumption). Mental health data, such as stress reported by the patients themselves, the history of consultation and the medication as well as their severity further enrich the data and increase clinical value of the whole data set.
The research design includes the process of cleaning and preparing both numeric and categorical features and creating new features and use supervised machine learning approaches to predict the degree of stress. The performance of such models as Random Forest, XGBoost, and Neural networks will be tested in terms of their accuracy, and statistical analysis will be introduced to consider the most important factors linked to occupational stress. The research goes further to compare the variation in stress by the different age groups, gender, regions with the aim of clarifying the stress pattern according to the different demographics.
The desired outcomes are the availability of a consistent and decipherable model that can suggest the levels of stress with a high degree of accuracy and identify dominant risk factors, i.e., a long working schedule, inadequate sleep, the absence of physical activity, and negative lifestyle choices. This knowledge can guide employers, policymakers, and mental health professionals to come up with more effective interventions, workplace programs on wellness, and early warning systems in regards to individuals considered at risk of developing chronic stress. This project will contribute to a growing body of research in the burgeoning field of computational mental health as well as to efforts to provide evidence-based support to the well-being of professionals.},
        keywords = {Occupational Stress, Machine Learning, Artificial Neural Networks (ANN), Stress Prediction, Computational Mental Health},
        month = {May},
        }