JURIKOM (Jurnal Riset Komputer)
Vol 10, No 1 (2023): Februari 2023

Penerapan Metode Clustering Dalam Pengelompokan Kasus Perceraian Pada Pengadilan Agama di Kota Pekanbaru Menggunakan Algoritma K-Medoids

Satria Bumartaduri (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Siska Kurnia Gusti (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Fadhilah Syafria (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Elin Haerani (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Siti Ramadhani (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)



Article Info

Publish Date
27 Feb 2023

Abstract

Divorce is the breaking of a husband and wife relationship from a marriage. When a couple does not want to continue their marriage relationship, one of the factors causing divorce is that the husband and wife do not carry out their duties properly. Divorce cases also occur in the city of Pekanbaru and have increased from 2020 to 2022. In connection with this problem, researchers conducted research with the aim of classifying districts in Pekanbaru that have the most divorces. The method used in this study is K-Medoids Clustering, because this method can divide a dataset into several groups. The advantage of this method is that it can overcome the weaknesses of the K-Means algorithm which are sensitive to outliers. The tests used in this study use the RapidMiner tools and the Davies Bouldin Index to ensure cluster accuracy. Attributes used in this research are region/regency, age difference between spouses, plaintiff's and defendant's education, and reasons for divorce. The results of this study can be used as information for the government to reduce the divorce rate in the city of Pekanbaru so that appropriate programs can be developed for each sub-district in overcoming the divorce rate in Pekanbaru. From testing using the K-Medoids algorithm, the cluster results obtained showed that the highest divorce rate was in cluster 1 with 565 items, while cluster 2 had 395 items and cluster 3 had 288 items. The results of the study show that the use of 3 clusters is the best cluster with a DBI value of 0.884.

Copyrights © 2023






Journal Info

Abbrev

jurikom

Publisher

Subject

Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Description

JURIKOM (Jurnal Riset Komputer) membahas ilmu dibidang Informatika, Sistem Informasi, Manajemen Informatika, DSS, AI, ES, Jaringan, sebagai wadah dalam menuangkan hasil penelitian baik secara konseptual maupun teknis yang berkaitan dengan Teknologi Informatika dan Komputer. Topik utama yang ...