Differing Roles of Leisure and Productivity in GDP - A Machine Learning based comparative analysis of Germany and USA
Title: Contrasting Impacts of Leisure and Output on National GDP: A Comparative Machine Learning Study of Germany and the USA
Abstract: This study models national Gross Domestic Product (GDP) as a function of the interplay between two key variables: working hours, which represent the societal preference for labor, and Total Factor Productivity (TFP), which signifies the aggregate investment in efficiency-enhancing technologies. We demonstrate that a Random Forest algorithm can effectively forecast GDP based on these two determinants. By employing Gini importance metrics, SHAP (SHapley Additive exPlanations) visualizations, and partial dependence plots, we analyze the divergent patterns observed in Germany and the United States. The results indicate that the distinct social frameworks of these two nations are mirrored in the varying degrees to which working hours and productivity contribute to their respective GDPs.
Source: arXiv Generated at: 2026-06-02 00:00:00 UTC
