<![CDATA[Economic growth is a critical macro indicator for regional development. Due to the nonlinear nature of economic fluctuations, traditional regression often fails to provide accurate forecasts. This research implements Support Vector Regression (SVR) to predict the economic growth of Pekalongan City based on BPS secondary data (2010–2024). The proposed framework includes data preprocessing, normalization, and Recursive Feature Elimination (RFE) for feature selection. We optimized the hyperparameters using Grid Search and k-fold cross-validation. The experimental results demonstrate that the SVR model with an RBF kernel outperforms traditional methods, reaching a MAPE of 3.82%. This study provides a robust computational approach for supporting evidence-based decision-making in local governance.]]>
Copyrights © 2026
