Classification of Receiving Electricity Subsidy Assistance in Blang Panyang Village Using the K-NN (K-Nearest Neighbor) Method

Abstract

The electricity subsidy program is one of the poverty reduction programs by providing electricity subsidy assistance funds to poor and disadvantaged households paid by the Government of Indonesia to PT PLN (Persero). The government implements a targeted electricity subsidy policy, the subsidy must be truly enjoyed by the poor. The purpose of this research is to test the K-Nearest Neighbors algorithm in predicting the receipt of electricity subsidy assistance. In the dataset of beneficiaries used in this study, there are 45 records or tuples with four attributes (house condition, income, occupation and number of amperes). The prediction of new data categories is done by using the manual calculation stage of Euclidean Distance from three different K values. The results show that with K=15, K=30 and K=45 the new data (46) has an "Ineligible" category with an accuracy rate of 100%. Then with K=45, K=30 and K=45 the new data (D46) has a "Viable" category with an accuracy rate of 66.6%.