Classification Analysis Of The Eligibility Of Recipients Of Non-Cash Food Assistance And Family Hope Programs In The City Of Sukabumi Using The Naïve Bayes Classifier Algorithm

Abstract

Providing social assistance is the government's effort to improve the welfare of the underprivileged. Non-Cash Food Assistance (BPNT) and the Family Hope Program (PKH) are two social assistance programs provided by the Indonesian government. BPNT is a food assistance program that is provided non-cash through electronic cards, while PKH is a cash social assistance program provided to poor families with certain criteria. Both programs aim to help the poor meet their food and education needs. To evaluate the effectiveness and efficiency of social assistance programs, a method is needed that can process and analyze data quickly and accurately. One method that can be used is the Naïve Bayes Classifier, which is a probabilistic classification method based on Bayes' theorem. This method can be used to classify data into certain categories based on its probability. In this study, researchers used the Naïve Bayes Classifier method to analyze social assistance data obtained from the BPNT and PKH programs. Data from the Sukabumi City Social Service was used to classify the eligibility of beneficiaries using the Naïve Bayes Classifier algorithm. Out of 5,183 data, 31.2% were classified as "Eligible" and 68.8% as "Ineligible". The algorithm showed 98.77% accuracy in eligibility classification. These results indicate the effectiveness of the Naïve Bayes Classifier algorithm in analyzing social data, providing new insights for better decision-making by relevant agencies in the development of more targeted and efficient social assistance policies