Verification of Covid-19 Social Assistance Recipients using Naïve Bayes Classifier

Abstract

The Indonesian government launches the Covid-19 social assistance program to reduce the impacts of the economic downturn during the pandemic. The recipients of social assistance in Sukabumi Selatan District of Jakarta Province is collected form Neighborhood Association (RT/RW). However, this mechanism has limitations in terms of feasibility assessment through direct verification which is not optimal due to social restriction activities. At the same time, data is also collected through the regular recipients of social aid program, so there is a data discrepancy that causing a bias in determining the recipients’ feasibility. Therefore, a mechanism is required to assess the eligibility of the recipients. This study aims to assist Social Service Agency of Sukabumi Selatan district, in assessing the eligibility of the recipients using Naïve Bayes classifier and K-Nearest Neighbors (K-NN) classifier as comparison. Experiments using Cross-Industry Standard Process for Data Mining (CRISP-DM) model were carried out on a collected dataset, and the results show that Naïve Bayes classifier shows the best result with 93% accuracy, 86% precision and 100% recall, while K-NN has 90% accuracy, 82% precision and 98% recall. This research may assist the Social Service Agency of the district to determining more accurately the target recipients.