Welcome to the InfoSci Platform
Reference Hub2
Prediction of Stress Level on Indian Working Professionals Using Machine Learning

Prediction of Stress Level on Indian Working Professionals Using Machine Learning

Kavita Pabreja, Anubhuti Singh, Rishabh Singh, Rishita Agnihotri, Shriam Kaushik, Tanvi Malhotra
Copyright: © 2022 |Volume: 13 |Issue: 1 |Pages: 26
ISSN: 1947-3478|EISSN: 1947-3486|EISBN13: 9781683181613|DOI: 10.4018/IJHCITP.297077
Cite Article Cite Article

MLA

Pabreja, Kavita, et al. "Prediction of Stress Level on Indian Working Professionals Using Machine Learning." IJHCITP vol.13, no.1 2022: pp.1-26. http://doi.org/10.4018/IJHCITP.297077

APA

Pabreja, K., Singh, A., Singh, R., Agnihotri, R., Kaushik, S., & Malhotra, T. (2022). Prediction of Stress Level on Indian Working Professionals Using Machine Learning. International Journal of Human Capital and Information Technology Professionals (IJHCITP), 13(1), 1-26. http://doi.org/10.4018/IJHCITP.297077

Chicago

Pabreja, Kavita, et al. "Prediction of Stress Level on Indian Working Professionals Using Machine Learning," International Journal of Human Capital and Information Technology Professionals (IJHCITP) 13, no.1: 1-26. http://doi.org/10.4018/IJHCITP.297077

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Stress levels amongst the Indian employees have increased due to a variety of factors and are a matter of great concern for the organizations. This study is based on Indian working professionals and real data has been collected by using non-probability convenience sampling. A questionnaire was drafted based on eighteen factors affecting the mental health of professionals. This study addresses two dimensions, first is to identify the important influential features that trigger stress in the lives of working professionals, and the second is to predict the stress levels. Various supervised machine learning algorithms have been experimented with and of all these algorithms, the Support Vector Machine Regressor model showed the best performance. The main contribution of the paper lies in the identification and ranking of ten important stress triggering features, that can guide organizations to develop policies to take care of their employees. The other deliverable is the development of a GUI-based stress prediction software based on Machine learning techniques.