Employee Burnout Prediction Using Data Sceince

Employee Burnout Prediction Using Data Sceince

,Umaira1, Ayshathul Sajeena1,Nusaiba1, Nabeesath Sunaina

1Department of Computer Science and Engineering, BIT, Mangaluru, Karnataka, India.

*Corresponding Author: Ayshathul Sajeena              Email: sajeenaacm@gmail.com

Abstract:
Nowadays employees face a lot of stress due to the workload and lack of leisure time, so it is the need of hour for having to predict and analyze employee burnout. One of the most important new concerns that organizations are grappling with is employee or job burnout. Workers in the manufacturing and service sectors who are frequently exposed to demanding work environments may become more stressed out at work, burn out, or even quit their jobs. Our research identifies the main causes of burnout by gathering and analyzing data from a variety of sources, such as performance indicators, questionnaires, and HR records.

The study makes use of machine learning models and statistical methods to find patterns and correlations in the data. Our goal is to forecast employee burnout occurrences by using predictive models, which will allow employers to take prompt action. To understand their impact on burnout, common contributing elements are investigated, including workload, job demands, interpersonal connections, and job satisfaction.

To identify trends and correlations in the data, the study uses statistical techniques and machine learning algorithms. Our objective is to use predictive models to anticipate employee burnout so that companies can respond promptly. The effects of typical contributing factors, such as workload, job demands, interpersonal relationships, and job satisfaction, on burnout are examined.

Key Words: Machine Learning, Burnout, prediction, Linear Regression, Ridge Regression, Lasso Regressor, catboost regressor