Work from Home Enhance Individual Productivity? A Predictive Analytics Using Machine Learning Towards Well-Being, Work -Life Balance, Technological and Organizational Support

Abstract

Purpose – This study aims to identify the main predictors of employee productivity among individuals who work from home. The research explores how well-being, work-life balance, focus, and organizational as well as technological support influence employees’ ability to perform effectively in a remote work setting. Methodology – Data were collected from 461 employees across various organizations. The study applied predictive analytics through several machine learning methods, including random forest and K-nearest neighbor algorithms, to test models related to individual productivity, well-being, work-life balance, organizational, and technological support. Findings – The results show that employee well-being, satisfaction, and work-life balance are the strongest predictors of productivity during work from home. The second strongest predictor is the ability to stay focused, followed by the ability to complete tasks on time and satisfaction with work-life balance. Technological support was found to be a necessary precondition to enhance productivity. Originality – This study contributes to the growing literature on remote work by integrating individual, organizational, and technological factors into a comprehensive predictive model that explains employee productivity in work-from-home settings.