<![CDATA[The classification of the Village Development Index (IDM) status is a fundamental component in formulating targeted and effective village development policies. However, the conventional classification process is often slow and inefficient, thereby reducing the data's relevance for dynamic decision-making. This research aims to design and evaluate an automatic classification model for the IDM status in 5,417 villages in North Sumatra Province using the Support Vector Machine (SVM) method. By utilizing secondary data from 2024, this model uses three main sub-indices—the Social Resilience Index (IKS), the Economic Resilience Index (IKE), and the Environmental Resilience Index (IKL)—as predictor variables to map villages into five status categories. The implementation of the SVM model with a Radial Basis Function (RBF) kernel was chosen to handle the complex non-linear relationships between variables. The evaluation results on the test data show superior performance, with an overall accuracy rate reaching 96.77%. The model's performance proved to be very strong, particularly in identifying the 'Developing' class with a perfect recall (1.00) and the 'Independent' class with perfect precision (1.00). Although minor challenges were found in distinguishing between adjacent classes such as 'Disadvantaged' and 'Developing', the high F1-score across all classes confirms a good balance between precision and recall. This study concludes that the SVM method is a highly reliable and valid approach for automating IDM classification, and it offers significant implications as a fast and accurate evidence-based decision support tool for local government]]>
Copyrights © 2025
