Poverty is still an ongoing problem in Indonesia, especially in Aceh Province, even though various interventions such as the Program Keluarga Harapan (PKH) and the use of the Kartu Keluarga Sejahtera (KKS) have been implemented. This study aims to classify social assistance recipients more accurately, in order to reduce poverty levels in Aceh Province. This study uses secondary data from the 2023 National Socio-Economic Survey (Susenas) with a total of 13,316 household observations and involving 28 independent variables. The results of the study show that the Classification Tree algorithm is able to classify households with an accuracy rate of 80%. The most influential variables in predicting KKS recipients include the education of the head of the household, floor area, number of household members, source of drinking water, and employment status. These findings indicate that a data-driven approach can improve the targeting accuracy of social assistance programs and support poverty alleviation efforts more effectively.