Age–Earnings Profiles Among Secondary Education Graduates: A Comparison of Econometric and Machine Learning Approaches for General and Vocational Education in Greece

Understanding earnings differences across general and vocational education is important for assessing labor-market outcomes among secondary education graduates. This study examines cross-sectional age–earnings profiles among full-time private-sector workers in Greece using survey data collected in 2020, with particular attention to differences between Gymnasium, General Lyceum (GEL), and Vocational Lyceum (EPAL) graduates. It also evaluates whether machine-learning methods provide additional predictive value beyond a conventional econometric benchmark using the same parsimonious age-related information set. Earnings are modeled using a quadratic OLS specification, Random Forest, and Gradient Boosting, with age and age squared used as predictors across all models. Predictive performance is assessed using R2, RMSE, and MAE, supplemented by repeated five-fold cross-validation and a cubic OLS robustness benchmark. The results indicate concave age–earnings profiles across educational groups, with higher earnings among upper secondary education graduates than Gymnasium graduates and higher earnings among GEL than among EPAL graduates. The predictive comparison shows that OLS remains a competitive benchmark, while machine-learning methods provide only modest and subgroup-dependent improvements. Overall, the findings show systematic cross-sectional earnings differences across educational levels and types, while the predictive advantages of machine-learning methods over the quadratic OLS benchmark remain modest.