Klasifikasi Keterlambatan Pembayaran Sumbangan Pembinaan Pendidikan Menggunakan Algoritma Naïve Bayes dan Support Vector Machine

Abstract

Payment delinquency of SPP is a commonly occurring issue in school. It affects the salary of teachers and staffs alongside school’s various development program. The study aims to classify payment delinquencies using Naïve Bayes and Support Vector Machine. Research methode is Cross-Industry Standard Process for Data Mining (CRISP-DM). Method testing was carried out with 5 trials. Based on the test results, the average performance of Naïve Bayes is accuracy (62,88%), precision (65,27%), recall (77,42%) dan f1-score (70,75%). Meanwhile, the average performance of the Support Vector Machine is accuracy 63,51%), precision (62,25%), recall (94,48%) dan f1-score (75,04%).