Open AccessMENGANALISIS KEMUNGKINAN KETERLAMBATAN PEMBAYARAN SPP DENGAN ALGORITMA C4.5 (STUDI KASUS POLITEKNIK TEDC BANDUNG)
Author(s) -
Tri Herdiawan Apandi,
Roby Bayu Maulana,
Rian Piarna,
Dwi Vernanda
Publication year - 2019
Publication title -
techno nusa mandiri/techno nusa mandiri
Language(s) - English
Resource type - Journals
eISSN - 2527-676X
pISSN - 1978-2136
DOI - 10.33480/techno.v16i2.659
Subject(s) - payment , confusion , partition (number theory) , confusion matrix , computer science , actuarial science , statistics , mathematics , business , artificial intelligence , psychology , world wide web , combinatorics , psychoanalysis
Payment of tuition as one of the sources of funds, plays an important role in the sustainability of the operations of higher education. The problem that arises is that students are not often late to make payments in a timely manner. One of the factors causing the many cases of late payment of tuition fees due to lack of policy and decisive action on the part of the campus when students are late in making payments, besides the factors of parents and students also have an influence on the delay. The purpose of this study is to classify students who are late and timely in making SPP payments using the C4.5 algorithm. From the total sample used then divided into 4 partitions, partition 1 for 90% training data and 10% testing data, partition 2 for 80% training data and 20% testing data, and partition 3 for 70% training data and 30% testing data , and partition 4 for 60% training data and 40% testing data. The classification results of the C4.5 algorithm are evaluated and validated with cross validation and confusion matrix to determine the accuracy of the C4.5 algorithm in predicting late SPP payments. Based on the comparison of the results of evaluations and validations conducted, it shows that data partition 2 has a better level of accuracy than the other partitions, which is 75%.
Keywords: Data Mining, Decision Tree (C4.5), SPP.