Perbandingan Naïve Bayes Dan C45 Dalam Klasifikasi Tes Kesehatan Mahasiswa Baru Akbid As-Syifa

Abstract

Medical test is important to determine the health of a person's body so they are often carried out and have even become one of the requirements for an institution to accept new members such as the As-Syifa Midwifery Academy which conducts medical tests for prospective new students. The problem is that so far the classification system for recapitulation of medical test results is still done manually, thus slowing the performance of the campus and it is feared that there will be damage to the data format. The problem solving technique above is carried out with a data mining process using Naïve Bayes and Decision Tree C45 where the two algorithms are compared to find the 1 best classification algorithm to be implemented in the system. The dataset uses data on the recapitulation of the results of the 2018 new student health tests sourced from the Administration (TU) of Akbid As-Syifa. The comparison uses 4 data testing models and the confusion matrix as the performance evaluation value of the modeling algorithm. The modeling results obtained that the Decision Tree C45 algorithm is superior and suitable to be implemented with an accuracy rate of 100% while Naïve Bayes has a maximum accuracy rate of 96%. The purpose of this study was to help Akbid As-Syifa classify the results of the health test of prospective new students.