<> "The repository administrator has not yet configured an RDF license."^^ . <> . . . "Decision Support System for Prioritizing Extreme Poverty \r\nAlleviation at the Provincial Level in Indonesia Using K-Means \r\nand Random Forest Algorithms"^^ . "Decision Support System for Prioritizing Extreme Poverty \r\nAlleviation at the Provincial Level in Indonesia Using K-Means \r\nand Random Forest Algorithms\r\nIldia Wati\r\nComputer Science Study Program, Faculty of Mathematics and Natural Sciences,\r\nPakuan University, Bogor City, West Java, 16143, Indonesia\r\nAbstract\r\nExtreme poverty remains one of the major challenges in Indonesia’s national development \r\nagenda, with disparities in the severity of poverty across provinces making it difficult to \r\nobjectively determine government intervention priorities. This study aims to develop a decision \r\nsupport system for identifying priority provinces for extreme poverty alleviation in Indonesia \r\nusing a hybrid approach that combines K-Means Clustering and Random Forest. Panel data \r\nobtained from Statistics Indonesia (BPS) for the period 2016–2025 were utilized, comprising \r\n34 provinces from 2016 to 2023 and 38 provinces from 2024 to 2025, resulting in 348 \r\nobservations. Seven indicators were employed: poverty rate, Gini ratio, Human Development \r\nIndex (HDI), Open Unemployment Rate (OUR), Economic Growth Rate (EGR), Poverty Gap \r\nIndex (P1), and access to improved sanitation. K-Means Clustering was first applied to \r\ngenerate three objective priority labels (low, medium, and high), which were subsequently used \r\nas training labels for the Random Forest classification model. Model performance was \r\nevaluated using 10-fold Group Cross-Validation to prevent data leakage in the panel data \r\nstructure, achieving an accuracy of 92.82%. Feature importance analysis revealed that the \r\nPoverty Gap Index (P1) was the most influential indicator (0.238), followed by the poverty rate \r\nand the Gini ratio, while the Economic Growth Rate contributed the least. The resulting model \r\nwas implemented in a Laravel-based web application, with a pure PHP inference service to \r\nensure that the classification results remained consistent with the model trained in Python. The \r\nproposed system provides an objective, data-driven decision support tool to assist \r\npolicymakers and researchers in prioritizing extreme poverty alleviation programs across \r\nIndonesian provinces.\r\nKeywords: extreme poverty; K-Means clustering; Random Forest; decision support system; provincial \r\nprioritizatio"^^ . "2026-07" . . "Universitas Pakuan"^^ . . . "Fakultas Matematika dan Pengetahuan Alam, Universitas Pakuan"^^ . . . . . . . . . . . "Ildia"^^ . "Wati"^^ . "Ildia Wati"^^ . . "Dian Kartika"^^ . "Utami"^^ . "Dian Kartika Utami"^^ . . "Lita"^^ . "Karlitasari"^^ . "Lita Karlitasari"^^ . . "Universitas Pakuan"^^ . . . "Fakultas Matematika dan Ilmu Pnegetahuan Alam"^^ . . . "Program Studi Ilmu Komputer"^^ . . . . . . "HTML Summary of #11228 \n\nDecision Support System for Prioritizing Extreme Poverty \nAlleviation at the Provincial Level in Indonesia Using K-Means \nand Random Forest Algorithms\n\n" . "text/html" . . . "Ilmu Komputer"@en . .