Penerapan Data Mining Untuk Menentukan Penerima Bantuan Pangan Non Tunai Menggunakan Metode K-Nearest Neighbor

Abstract

Poverty is a problem that exists in all countries in the world, including Indonesia. Many subsidy programs are provided by the Indonesian government to the community to reduce and assist the community in reducing poverty levels including by providing non-cash food assistance. The purpose of this research is to build and develop a decision support system to assist local governments in determining the eligibility of non-cash assistance recipients in Bireuen Regency and to determine the accuracy of the methods used. The data mining technique used in this research is classification with the K-Nearest Neighbor method. The stages used in this research begin with literature study, data collection, system requirements analysis, system design, system testing and system implementation. The dataset of aid recipients used in this study is 200 data using three variables, namely income, house condition and number of dependents, then the data is manually calculated using the K-Nearest Neighbor method to determine the classification. From the amount of data used in this system, it produces an accuracy rate of 89%, recall 93% and precision 96%. The results of research using the K-Nearest Neighbor method can be used to solve problems in determining the eligibility of non-cash food assistance recipients.