<![CDATA[Determining the eligibility of social assistance recipients is an important stage in the government’s effort to distribute aid accurately to people who truly need it. In practice, however, the selection process often encounters problems, particularly inaccurate targeting caused by manual assessment. This study aims to implement the Naive Bayes algorithm to determine the eligibility of social assistance recipients in Heram Village. The dataset used in this study consisted of 358 records, divided into 251 training data and 107 testing data. Before the modelling process, the data were cleaned and selected so that only relevant variables were used in the classification process. The attributes applied in this study included gender, age, occupation, number of dependents, dependent category, priority category, monthly income, income category, housing condition, asset ownership, and employment status, with actual eligibility as the class label. The stages of data processing, modelling, and evaluation were carried out using RapidMiner software. The results showed that the Naive Bayes model achieved an accuracy of 85.05%, precision of 83.33%, recall of 86.54%, and AUC of 0.924, which is categorized as excellent classification. These findings indicate that the Naive Bayes algorithm is effective and feasible to be used as a decision-support method in determining social assistance recipient eligibility in a more objective, systematic, and measurable manner in Heram Village.]]>
Copyrights © 2026
