Prediksi Tingkat Kesehatan Masyakarat Berdasarkan Penggunaan Alat Kontrasepsi Menggunakan Algoritma Random Forest

Abstract

Public health is part of a lifestyle that is used to prevent disease, extend life span, and improve the quality of human resources. Therefore, it is very necessary to study public health from various aspects, so that the goals and targets to be achieved can be realized. One of the studies presented was the use of contraceptives for rural communities, especially rural communities in Suralaga District, East Lombok Regency - West Nusa Tenggara. The use of contraceptives, which is one of the methods used in implementing family planning, is still at a relatively low level. Based on the data held relating to this matter, analysis and data processing are needed in determining the decisions to be taken to determine the effect of contraceptives in improving public health. Data processing and analysis is carried out using the Random Forest algorithm, which is due to the appropriate characteristics of the datasets used. To get the best results or performance in determining the level of accuracy, the datasets used have 10 attributes, namely: full name, age, last education, couple of childbearing age, age at first pregnancy, age at first birth, ready for birth control, contraceptives, following the contact program, and birth distance. The accuracy obtained was 71.99% with the decision tree output that the most common and efficient contraceptives used in the Suralaga District area were birth control pills and birth control injections.