ALENDIA, NENSIA (2021) STUDI KOMPARASI ALGORITMA CLUSTERING DALAM MEMETAKAN STATUS PEREKONOMIAN MASYARAKAT DI KELURAHAN CIPADU KOTA TANGERANG. S1 thesis, Universitas Mercu Buana Jakarta.
![]() |
Text (HAL COVER)
01 COVER - NENSIA ALENDIA.pdf Download (1MB) |
![]() |
Text (BAB I)
02 BAB 1 - NENSIA ALENDIA.pdf Restricted to Registered users only Download (117kB) |
![]() |
Text (BAB II)
03 BAB 2 - NENSIA ALENDIA.pdf Restricted to Registered users only Download (330kB) |
![]() |
Text (BAB III)
04 BAB 3 - NENSIA ALENDIA.pdf Restricted to Registered users only Download (41kB) |
![]() |
Text (BAB IV)
05 BAB 4 - NENSIA ALENDIA.pdf Restricted to Repository staff only Download (109kB) |
![]() |
Text (BAB V)
06 BAB 5 - NENSIA ALENDIA.pdf Restricted to Registered users only Download (56kB) |
![]() |
Text (DAFTAR PUSTAKA)
08 DAFTAR PUSTAKA - NENSIA ALENDIA.pdf Restricted to Registered users only Download (37kB) |
![]() |
Text (LAMPIRAN)
09 LAMPIRAN - NENSIA ALENDIA.pdf Restricted to Registered users only Download (382kB) |
Abstract
This study discusses the comparison of the Meanshift Clustering Algorithm, K-Means and K-Medoids in clustering and the results will be proposed to be taken into consideration by the local government in grouping people based on their economic status.Socio-economic mapping will be carried out using a data mining approach, especially using the Clustering Mean Shift, K-Means and K-Medoids algorithms. These three algorithms will be compared to get the best results. The results of the clustering will later be used as a profile of existing status in the Cipadu village community, Tangerang City. The data obtained were 862 with the attributes of the number of household members, work status, building status, floor area, installed power, type of floor, roof condition and drinking source. This study uses Dunn Index validation. Based on the results of cluster quality testing with Dunn Index validation, the value of the Mean Shift Algorithm analysis is 0.887, then the K-Means results are 0.995 and K-Medois is 0.880. So from the three algorithms it can be concluded that the K-Means Clustering algorithm has the best value because it is closest to number 1. Key words: Economic Status, Mean shift, K-Means, K-medoids, Clustering, Data Mining Penelitian ini membahas mengenai perbandingan Algoritma Meanshift Clustering, K-Means dan K-Medoids dalam klasterisasi dan hasilnya akan diusulkan untuk menjadi bahan pertimbangan pemerintah setempat dalam mengelompokkan masyarakat berdasarkan status perekonomiannya. Pemetaan sosial ekonomi akan dilakukan dengan menggunakan pendekatan data mining khususnya menggunakan algoritma Clustering Mean Shift , K-Means dan K-Medoids ketiga algoritma ini akan dibandingkan untuk mendapatkan hasil yang terbaik. Hasil clustering nantinya akan dijadikan sebagai profil status yang ada dimasyarakat kelurahan Cipadu Kota Tangerang. Didapatkan data sejumlah 862 data dengan atribut Jumlah anggota rumah tangga, status pekerjaan, status bangunan, luas lantai, daya terpasang, jenis lantai, kondisi atap dan sumber minum. Penelitian ini menggunakan validasi Dunn Index. Berdasarkan hasil pengujian kualitas cluster dengan validasi Dunn Index di dapatkan nilai dari hasil analisis Algoritma Mean shift sebesar 0.887, kemudian di dapatkan hasil K-Means sebesar 0.995 dan K-Medoids sebesar 0.880 Maka dari ketiga algoritma tersebut dapat ditarik kesimpulan bahwa algoritma K-Means Clustering memiliki nilai yang paling baik karena paling mendekati angka 1. Kata kunci: Status Ekonomi, Meanshift, K-Means, K-medoids, clustering, Data Mining
Actions (login required)
![]() |
View Item |