Machine Learning for Wage Growth Prediction: Analyzing the Role of Experience, Education, and Union Membership in Workforce Earnings Using Gradient Boosting

Abstract

This research investigates the application of machine learning, specifically gradient boosting, to predict wage growth by analyzing the roles of experience, education, and union membership. As labor market dynamics become increasingly complex, accurate wage prediction models are essential for informing workforce planning and educational strategies. This study utilizes a dataset that includes variables such as years of experience, education level, union affiliation, and industry type. Gradient boosting, a powerful ensemble learning algorithm, is employed to predict wages and is evaluated against a baseline linear regression model. The model’s performance is assessed using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), showing that gradient boosting significantly outperforms linear regression in terms of predictive accuracy. Feature importance analysis reveals that education level (schooling) is the most influential factor in wage prediction, followed by years of experience, union membership, and marital status. The study highlights the importance of education and union support in driving wage growth, offering valuable insights for policymakers and workforce planners. Despite promising results, limitations such as dataset constraints and the need for broader socioeconomic factors suggest avenues for future research. Further exploration into the integration of alternative machine learning algorithms, such as Random Forest or Neural Networks, and the inclusion of more diverse variables could improve model robustness and generalizability. The findings have practical applications in AI-powered workforce development systems, offering a data-driven approach to career guidance, educational planning, and labor market policy development. This research underscores the potential of AI and machine learning to enhance economic modeling and workforce development strategies.