Regional innovation and economic growth: Empirical insights from FGLS, FE-DKSE, and XGBoost-SHAP approach

Abstract

This study examines the impact of regional innovation factors and their dynamic interactions on regional economic growth. Using a 10-year panel dataset from 17 provinces and cities in South Korea, we analyze the data using panel data regression and explore non-linear relationships with the XGBoost model. We also enhance the model's interpretability by analyzing the impact of the variables on the predictions through Shapley Additive Explanations (SHAP) analysis. In the FGLS analysis, the number of innovative regional firms positively impacted GRDP, suggesting innovative firms boost regional economic output, but had minimal effect on Per Capita Gross Value Added (PCGVA). The proportion of top universities showed no significant impact on GRDP or PCGVA, though XGBoost and SHAP analyses indicated a complex, negative relationship with PCGVA. The interaction between the proportion of top universities and the number of innovative regional firms positively affected GRDP, emphasizing universities' role in supporting innovative firms. The effect of government R&D investment support on PCGVA highlights the importance of appropriate levels of support for maximizing productivity. The results indicate that R&D investment and open innovation significantly influence regional economic growth, with their effects exhibiting non-linear relationships. High-tech and medium-tech industries drive regional economic growth, while low-tech sectors have a negative impact on growth and per capita value-added. This study offers policy implications for fostering regional economic development as well as insights into the intricate links between economic growth and regional innovation factors.