<![CDATA[Educational equity remains one of the major challenges in human resource development in Indonesia. Differences in the availability of educational facilities across regions may affect the quality of educational services and widendevelopment disparities. This study aims to classify educational access levels across regencies/cities in Central Kalimantan Province based on educational facility availability using the Support Vector Machine (SVM) algorithm. Aquantitative approach was employed using secondary data obtained from Statistics Indonesia (BPS) in 2025, consisting of the number of elementary schools, junior high schools, senior high schools, vocational schools, and higher education institutions across 13 regencies/cities. The research procedures included data preprocessing, Min-Max normalization, category labeling usingtertile classification, training-testing data splitting, and SVM model development. Model performance was evaluated using a confusion matrix and accuracy measurement. The findings indicate that most regencies/cities fallwithin the moderate educational access category, while only a few belong to the high and low categories. The SVM model successfully identified patterns in the distribution of educational facilities with a very high level of accuracy. These results demonstrate the potential of machine learning approaches as decisionsupport tools for educational development planning. Practically, the findings can assist policymakers in prioritizing educational infrastructure development in underserved regions ]]>
Copyrights © 2026
