KLASIFIKASI PENERIMA PROGRAM KELUARGA HARAPAN MENGGUNAKAN METODE RANDOM FOREST PADA KELURAHAN 13 ULU SEBERANG ULU DUA PALEMBANG

Abstract

The Family Hope Program (Program Keluarga Harapan, PKH) is a social assistance program aimed at helping poor and vulnerable families. This program is provided to families registered in the Unified Database for Social Welfare (DTKS) and meet certain criteria, such as having school-aged children, toddlers, pregnant women, or elderly members. In its implementation, PKH distribution often faces challenges, such as inaccurate targeting and insufficiently detailed data on poor families. Therefore, this research aims to classify PKH beneficiaries in 13 Ulu Village, Seberang Ulu II District, Palembang, to ensure that social assistance is given to those who truly meet the eligibility criteria. The method used in this research is the Random Forest method, which involves several stages. These stages include Data Preprocessing, Data Splitting, Random Forest Method Implementation, and Evaluation. Several attributes used in this research include House Ownership, Number of Children, School-Aged Children, Toddlers, Pregnant Women, Elderly, Occupation, and Income, with the target attribute being PKH eligibility. In this research, 117 datasets were used, which had gone through the Preprocessing stage. The data was then split with a 70:30 ratio for training and testing, resulting in an accuracy of 97%, precision of 96%, recall of 100%, and an F1-Score of 98%. These results indicate that the Random Forest method is quite effective in accurately classifying PKH beneficiaries.