<![CDATA[Access to accurate family economic data is essential for the equitable distribution of village social assistance. At the Popalia Village Office, Tanggetada Sub-district, Kolaka Regency, identification of eligible recipients previously relied on manual, page-by-page verification of Statistics Indonesia (BPS) census documents, a process that was slow and often produced recipients that did not match the intended criteria. This study develops a web-based classification system using the K-Nearest Neighbor (KNN) algorithm to categorize 160 household heads into “Mampu” (financially capable) and “Tidak Mampu” (financially incapable) classes based on twelve socio-economic criteria, including occupation, monthly income, education, number of dependents, and asset ownership. The system was built following the Waterfall development model using PHP and MySQL with a use-case-driven UML design. Model performance was evaluated using Euclidean-distance-based KNN with 10-fold cross validation and confusion matrix analysis. The system achieved an average classification accuracy of 99.38% (minimum 93.75%, maximum 100%), a precision of 98.21%, a recall of 100%, and an F1-score of 99.10%. Black-box testing further confirmed that all functional modules operated as intended. These findings indicate that KNN is an accurate and practical method for supporting village-level social assistance targeting.]]>
Copyrights © 2026
