Impact of AI and ML on Employee Job Satisfaction and Performance

This research thoroughly investigates the impact of machine learning (ML) and artificial intelligence(AI) on employee work performance as well as job contentment. Six distinct algorithms were evaluated: Random Forests, XGBoost, AdaBoost, Support Vector Regression(SVR), Decision Trees, and Linear Regression for predicting staff satisfaction and efficiency based on factors such as department, experience level, access to training, and other variables. The investigation employs data preprocessing techniques, like StandardScaler, to ensure each feature contributes equally to the analysis, and uses train-test splitting to separate information for training and evaluating models. Among the algorithms tested, SVR emerged as the top performing model, displaying superior precision in anticipating worker outcomes. SHAP values are used to point the components that significantly affect the model's forecasts of productivity and satisfaction. Some employees thrive in roles that continuously introduce them to new problems, whereas others prefer tasks that do not frequently change. This methodology offers an inter-pretable and accurate way to identify and evaluate most relevant factors of employee outcomes. With the power of these cutting-edge ML methods, organisations can delve deeper into analyzing their employees' performance. This data-driven approach will result in better work environment, focused training programs and finally a happy working force. The study reiterates the promise of AI-ML in addressing intricate workplace nuances to drive strategic workforce policy changes meant to boost employee happiness, and organisational efficiency.