<![CDATA[Gender inequality in Indonesia is a multidimensional problem that has a wide impact on human development. This study aims to model and classify the level of gender inequality between provinces in Indonesia with a combined approach of unsupervised and supervised learning. Secondary data from 38 provinces in 2024 were analyzed using five methods: K-Means, Self-Organizing Map (SOM), hybrid SOM-KMeans, Support Vector Machine (SVM), and Logistic Regression. In the unsupervised approach, the SOM and SOM-KMeans methods show better cluster coherence than K-Means. In the supervised approach, the SVM method provides better classification performance compared to logistic regression. Overall, SVM was obtained with the highest accuracy, which was 89.47%, surpassing other methods. This research makes a methodological contribution to the use of machine learning for spatial-based gender inequality risk mapping, as well as implications for more precise and adaptive data-based policymaking.]]>
Copyrights © 2026
