Pemodelan Klasifikasi Kesejahteraan Rumah Tangga dengan MARS, Suatu Studi Kasus di Kota Medan

Abstract

This study aims to look at the factors that become identifier in the field of household welfare and how these models are built to a high enough classification accuracy. The model used is Bagging MARS. The results of this study showed that of the nine variables studied, seven of which have contributed to the model, the number of household members, household drinking water sources, education of household head, employment status of household head, gender of household head, age of head of household stairs, and main industry of household heads. While the classification accuracy produced by MARS method is 94.08%. The application of bagging technique can improve the classification of 95.04%.