<![CDATA[Rural development plays a crucial role in reducing economic disparities, particularly in West Java, which comprises 5,311 villages with substantial variation in the Village Development Index (Indeks Desa Membangun/IDM). This study develops a machine-learning-based predictive model to classify villages’ economic intervention needs by utilizing multidimensional data—economic, social, and infrastructure indicators—sourced from BPS and the Ministry of Villages. Three machine learning algorithms—Random Forest, Gradient Boosting, and XGBoost—were evaluated using the 2023 West Java IDM dataset, which includes several relevant variables.The preprocessing stage involved handling missing values, data normalization, and data transformation, while hyperparameter optimization using GridSearchCV significantly improved model accuracy. The results indicate that XGBoost outperformed the other algorithms, achieving an accuracy of 88% and an F1-score of 0.93, particularly excelling in identifying autonomous villages (Class A) and high-intervention villages (Class D). Key contributing variables included the availability of financial services and the number of micro-industries.The model was integrated into an interactive dashboard built with Dash to support policymakers in conducting multi-level analyses (village/subdistrict/regency) and formulating evidence-based recommendations. The findings of this study have important implications for enhancing the efficiency of resource allocation and improving policy transparency, aligning with Bappenas' initiative to implement the Village Index starting in 2025. Overall, this research reinforces the importance of data-driven approaches for targeted and sustainable rural development]]>
Copyrights © 2026
