Optimizing Employee Satisfaction with Health and Safety Using Computational Models and Machine Learning

The study scrutinizes employee satisfaction concerning health and safety measures in a manufacturing company, highlighting its critical influence on organizational productivity and employee welfare. Amid heightened global focus and regulatory scrutiny, this research identifies a profound gap in understanding the direct relationship between comprehensive safety protocols and employee satisfaction in industrial settings. By employing Principal Component Analysis (PCA) and the CatBoostRegressor, enhanced by SHAP value analysis, the study deciphers complex data to reveal significant dimensions of workplace satisfaction. Findings indicate that while the company has robust safety measures, critical areas require enhancement to significantly improve employee satisfaction and overall organizational health. This paper offers evidence-based strategies for improving physical and psychological safety measures, fostering a more satisfied workforce. It contributes to occupational safety discourse and provides strategic insights for enhancing workplace conditions, advocating a holistic approach to employee well-being in industrial environments.