cover
Contact Name
Oman Somantri
Contact Email
ejournal.jict@gmail.com
Phone
-
Journal Mail Official
ejournal.jict@gmail.com
Editorial Address
-
Location
Kota cirebon,
Jawa barat
INDONESIA
Jurnal ICT : Information Communication & Technology
Published by STMIK IKMI Cirebon
ISSN : 23020261     EISSN : 23033363     DOI : -
Core Subject : Science,
Jurnal ICT : Information Communication & Technology (JICT) (p-ISSN: 2302-0261, e-ISSN: 2303-3363 ) is a scientific journal and open access journal published by Lembaga Penelitian dan Pengabdian Masyarakat (LPPM) of STMIK IKMI Cirebon, Indonesia. Jurnal JICT covers the field of Informatics, Computer Science, Information Technology and Communication. It was firstly published in 2012 for a printed version. The aims of Jurnal JICT are to disseminate research results and to improve the productivity of scientific publications. Jurnal JICT is published two times a year (July and December).
Arjuna Subject : -
Articles 1 Documents
Search results for , issue "Vol. 21 No. 1 (2022): JICT-IKMI, Juli 2022" : 1 Documents clear
Performa Algoritma Data Mining Untuk Klasifikasi Data Perceraian Elvin Leander Hadisaputro
Jurnal ICT: Information Communication & Technology Vol. 21 No. 1 (2022): JICT-IKMI, Juli 2022
Publisher : LPPM STMIK IKMI Cirebon

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Data mining is the process of analyzing data to find patterns from existing data to produce useful information. One type of data mining is classification, which distinguishes a data object from another. There are several algorithms for classification. This study looks for the best performance of data mining algorithms for decision tree classification, nave Bayes, k-nearest neighbors, neural networks and Support Vector Machines. Performance is seen without using feature selection and using feature selection found in the RapidMiner application, namely Backward Elimination and Forward Selection. The data used is data on divorce cases at the Penajam Religious Court from 2018-2020. 2018-2019 data is used as training data and 2020 data is used as test data. The best performance found from the use of test data is the nave Bayes algorithm that uses Backward Elimination with an accuracy value of 81.72% and AUC 0.691.

Page 1 of 1 | Total Record : 1