<![CDATA[The Provincial Government of DKI Jakarta has a social assistance program budgeted by the APBD in the form of the Jakarta Elderly Card (KLJ), Jakarta Persons with Disabilities Card (KPDJ) and Jakarta Child Card (KAJ) programs. The problems that occur at the Kelurahan level are related to social assistance, namely the difficulty in determining the right type of assistance to be received by residents according to the terms and criteria that have been determined by the Government and there is no overlapping of recipients of assistance. The registration factor and the lack of understanding of residents regarding the criteria for the type of social assistance resulted in the determination of recipients of social assistance not being on target, such as residents receiving assistance who did not meet the criteria, resulting in social jealousy. To help with this problem, research was carried out to determine the best model in classifying the types of social assistance based on recipient criteria by comparing three classification methods. This study uses 100 respondent data and 8 criteria used as determinants of recipients. Comparison of the Certainty Factor, Naïve Bayes and Decision Tree models will provide an overview of the best model based on the level of accuracy. The confusion matrix is used to test the accuracy for Naïve Bayes and Decision Tree and the output of the selected model is a web-based application that can provide recommendations for types of social assistance. The best accuracy results are Certainty Factor which is 98.4%, Naïve Bayes and Decision Tree is 93.3%.]]>
Copyrights © 2022
