Classification eligibility recipient BPJS in ward sendang sari using the naive bayes method

Abstract

Study This done for classify eligibility BPJS recipients in the sub-district Sendang Sari with use Naive Bayes method, which is relevant in support transparency and efficiency distribution benefit guarantee social at the level sub-district. Problems main in study This is Still its use manual system in the classification process, which causes the decision-making process decision become slow, subjective and vulnerable error. Research methods involving collection of 1000 citizen data Ward Sendang Sari which consists of from attributes like type gender, employment status, ownership house, income, and amount liability. Data then through preprocessing stage, including conversion variable categorical use LabelEncoder and determination of eligibility labels based on threshold income and amount liability. Next, the data is divided into training data and test data with 80:20 ratio. Classification model built use Gaussian Naive Bayes algorithm and evaluated use confusion matrix metrics which include accuracy, precision, and recall. Evaluation results show that the model achieves accuracy of 0.97 or 97%, precision of 0.95 or 95%, and recall of 0.90 or 90%, and F1-Score of 0.93 or 93 % which to signify that this model Enough effective For classify eligibility BPJS recipients. Research This conclude that The Naive Bayes method is capable of give accurate and consistent classification, which can increase efficiency administration ward as well as speed up distribution benefit to entitled community.