<![CDATA[Regional economic structures reflect the characteristics of economic activity across regions. This study aims to identify predictive factors that contribute to regional economic structures in Indonesia by modeling the contribution of 17 economic sectors to Regional Gross Domestic Product (RGDP). The data cover 34 provinces from 2015 to 2021, comprising 238 observations. Multi-Output Extreme Gradient Boosting (XGBoost) was used to predict the contribution of each sector, while SHapley Additive exPlanations (SHAP) was used to identify the variables with the greatest predictive contribution. The results show high predictive performance, with R² values for the test data ranging from 0.86 to 0.99, while cross-validation yielded average R² values ranging from 0.80 to 0.94. The SHAP analysis indicates that demographic characteristics, investment, and human development have high predictive contributions, with varying patterns across sectors. These findings suggest that XGBoost and SHAP can be used to interpretatively map the predictive patterns of regional economic structures, without claiming causal relationships or statistical significance.]]>
Copyrights © 2026
