Repository Universitas PakuanDecision Support System for Prioritizing Extreme Poverty Alleviation at the Provincial Level in Indonesia Using K-Means and Random Forest AlgorithmsIldiaWatiauthorDecision Support System for Prioritizing Extreme Poverty Alleviation at the Provincial Level in Indonesia Using K-Means and Random Forest Algorithms Ildia Wati Computer Science Study Program, Faculty of Mathematics and Natural Sciences, Pakuan University, Bogor City, West Java, 16143, Indonesia Abstract Extreme poverty remains one of the major challenges in Indonesia’s national development agenda, with disparities in the severity of poverty across provinces making it difficult to objectively determine government intervention priorities. This study aims to develop a decision support system for identifying priority provinces for extreme poverty alleviation in Indonesia using a hybrid approach that combines K-Means Clustering and Random Forest. Panel data obtained from Statistics Indonesia (BPS) for the period 2016–2025 were utilized, comprising 34 provinces from 2016 to 2023 and 38 provinces from 2024 to 2025, resulting in 348 observations. Seven indicators were employed: poverty rate, Gini ratio, Human Development Index (HDI), Open Unemployment Rate (OUR), Economic Growth Rate (EGR), Poverty Gap Index (P1), and access to improved sanitation. K-Means Clustering was first applied to generate three objective priority labels (low, medium, and high), which were subsequently used as training labels for the Random Forest classification model. Model performance was evaluated using 10-fold Group Cross-Validation to prevent data leakage in the panel data structure, achieving an accuracy of 92.82%. Feature importance analysis revealed that the Poverty Gap Index (P1) was the most influential indicator (0.238), followed by the poverty rate and the Gini ratio, while the Economic Growth Rate contributed the least. The resulting model was implemented in a Laravel-based web application, with a pure PHP inference service to ensure that the classification results remained consistent with the model trained in Python. The proposed system provides an objective, data-driven decision support tool to assist policymakers and researchers in prioritizing extreme poverty alleviation programs across Indonesian provinces. Keywords: extreme poverty; K-Means clustering; Random Forest; decision support system; provincial prioritizatioIlmu Komputer2026-07Universitas Pakuan;Fakultas Matematika dan Pengetahuan AlamThesis

For work being deposited by its own author: In self-archiving this collection of files and associated bibliographic metadata, I grant Repository Universitas Pakuan the right to store them and to make them permanently available publicly for free on-line. I declare that this material is my own intellectual property and I understand that Repository Universitas Pakuan does not assume any responsibility if there is any breach of copyright in distributing these files or metadata. (All authors are urged to prominently assert their copyright on the title page of their work.)

For work being deposited by someone other than its author: I hereby declare that the collection of files and associated bibliographic metadata that I am archiving at Repository Universitas Pakuan) is in the public domain. If this is not the case, I accept full responsibility for any breach of copyright that distributing these files or metadata may entail.

Clicking on the deposit button indicates your agreement to these terms.