<![CDATA[This research aims to classify social assistance recipients to ensure the accuracy of aid distribution by utilizing the Gradient Boosting algorithm on RapidMiner. The data used is data on residents who are categorized as receiving and not receiving social assistance in Cicadas village with a total dataset consisting of 670 entries with 18 attributes that will be divided equally between eligible and ineligible recipients. This research uses KDD (Knowledge Discover in Database) analysis which includes the stages of data selection, pre-processing, transformation, modeling, and interpretation of results. This research uses a quantitative approach, focusing on the distribution of datasets in a ratio of 70:30 with a stratified sampling technique for training and testing purposes. The experimental results show that the selected method is effective in classifying recipients by obtaining an accuracy of 91.67%, this accuracy result can be relied upon to support decision-making in social assistance distribution. The findings underscore the potential of machine learning in optimizing social welfare initiatives by improving target accuracy and ensuring aid reaches the rightful recipients.]]>
Copyrights © 2025
