Open AccessPENANGANAN KLASIFIKASI KELAS DATA TIDAK SEIMBANG DENGAN RANDOM OVERSAMPLING PADA NAIVE BAYES (Studi Kasus: Status Peserta KB IUD di Kabupaten Kendal)
Author(s) -
Reza Dwi Fitriani,
Hasbi Yasin,
Tarno Tarno
Publication year - 2021
Publication title -
jurnal gaussian : jurnal statistika undip
Language(s) - English
Resource type - Journals
ISSN - 2339-2541
DOI - 10.14710/j.gauss.v10i1.30243
Subject(s) - naive bayes classifier , oversampling , bayes' theorem , family planning , population , statistics , mathematics , computer science , medicine , artificial intelligence , research methodology , bayesian probability , environmental health , computer network , bandwidth (computing) , support vector machine
The Family Planning Program (KB) launched by the Government of Indonesia to address the problem of population control does not always produce the desired program results. In 2017, there were 7 users of the IUD contraceptive type of contraceptive who failed from 1,102 new IUD users in Kendal Regency so that the ratio of success and failure to the IUD KB program when compared to users of the new IUD KB is 0.64%: 99.36% . The ratio of success and failure of family planning programs which tend to be unbalanced makes it difficult to predict. One of the handling imbalanced data is oversampling, for example using Random Oversampling (ROS). Naive Bayes is used for classification because it’s easy and efficient learning model. The data in this study used 14 independent variables and 1 dependent variable. The results of this study indicate that the G-mean of Naive Bayes is less than 60%. The G-mean of ROS-Naive Bayes is 96.6%. It can be concluded that in this research, the ROS-Naive Bayes method is better than the Naive Bayes method for detecting the success status of IUD family planning in Kendal Regency. Keywords: Naive Bayes, Random Oversampling, G-mean