PENERAPAN DATA MINING PADA PENJUALAN PRODUK DIGITAL (PULSA) KONTER BUTET CELL MENGGUNAKAN METODE K-MEANS CLUSTERING

AFRIANSYAH AZAHAR, NPM 2109100104 (2025) PENERAPAN DATA MINING PADA PENJUALAN PRODUK DIGITAL (PULSA) KONTER BUTET CELL MENGGUNAKAN METODE K-MEANS CLUSTERING. Skripsi thesis, Universitas Labuhanbatu.

	Text COVER.pdf Download (565kB)
	Text BAB I.pdf Download (70kB)
	Text BAB II.pdf Download (339kB)
	Text BAB III.pdf Download (422kB)
	Text BAB IV.pdf Download (1MB)
	Text BAB V.pdf Download (72kB)
	Text DAFTAR PUSTAKA.pdf Download (190kB)

Abstract

Kemajuan teknologi informasi telah mendorong pemanfaatan data transaksi dalam dunia bisnis, termasuk pada sektor ritel pulsa. Namun, banyak usaha kecil seperti Konter Butet Celluler masih menghadapi kendala dalam mengolah dan menganalisis data transaksi agar dapat dimanfaatkan sebagai dasar strategi pemasaran yang efektif. Penelitian ini bertujuan untuk mengaplikasikan algoritma K-Means Clustering dalam mengelompokkan data penjualan pulsa sehingga pola pembelian pelanggan dapat diidentifikasi secara lebih jelas dan akurat. Data yang digunakan merupakan data transaksi penjualan pulsa pada periode January-Juni 2023, yang mencakup atribut jenis operator, nominal, jumlah penjualan, serta bulan transaksi. Tahapan penelitian meliputi pengumpulan data, preprocessing, penerapan algoritma K-Means, evaluasi hasil clustering menggunakan Euclidean Distance, serta validasi model dengan metrik evaluasi Silhouette Score dan Davies Bouldin Index. Implementasi dilakukan secara manual dengan perhitungan iteratif dan dibantu perangkat lunak RapidMiner 10.3. Hasil penelitian menunjukkan bahwa data penjualan pulsa dapat terbagi ke dalam tiga cluster, yaitu produk laris, produk sedang diminati, dan produk kurang diminati. Hasil Clustering data K3, Cluster 0 sebanyak 17 item, Cluster 1 sebanyak 6 item danterakhir Cluster 2 sebanyak 18 item. Informasi ini memberikan gambaran mengenai perilaku pembelian pelanggan yang dapat dimanfaatkan untuk menyusun strategi pemasaran, pengelolaan stok, serta peningkatan efisiensi operasional. Dengan demikian, penelitian ini berkontribusi dalam pengembangan penerapan data mining, khususnya metode K-Means Clustering, pada bisnis ritel skala kecil sekaligus menjadi referensi akademis untuk penelitian selanjutnya. Kata Kunci: Data Mining, Clustering, K-Means, Penjualan Pulsa, Konter Butet Celluler ======================================================================================== The advancement of information technology has encouraged the utilization of transactional data in the business world, including the prepaid credit retail sector. However, many small businesses such as Konter Butet Celluler still face challenges in processing and analyzing transactional data so that it can be used as a basis for effective marketing strategies. This study aims to apply the K-Means Clustering algorithm in grouping prepaid credit sales data in order to identify customer purchasing patterns more clearly and accurately. The data used consists of prepaid credit sales transactions during the January-June 2023 period, which include attributes such as operator type, nominal value, sales volume, and transaction month. The research stages include data collection, preprocessing, application of the K-Means algorithm, clustering evaluation using Euclidean Distance, and model validation with evaluation metrics such as Silhouette Score and Davies-Bouldin Index. The implementation was carried out manually through iterative calculations and supported by RapidMiner 10.3 software. The results indicate that prepaid credit sales data can be grouped into three clusters, namely best-selling products, moderately demanded products, and less demanded products. The clustering results of data K3 show that Cluster 0 contains 17 items, Cluster 1 contains 6 items, and Cluster 2 contains 18 items. This information provides insights into customer purchasing behavior that can be utilized for developing marketing strategies, stock management, and improving operational efficiency. Thus, this study contributes to the development of data mining applications, particularly the K-Means Clustering method, in small-scale retail businesses while also serving as an academic reference for future research. Keywords: Data Mining, Clustering, K-Means, Prepaid Credit Sales, Konter Butet Celluler

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Data Mining, Clustering, K-Means, Penjualan Pulsa, Konter Butet Celluler===============Data Mining, Clustering, K-Means, Prepaid Credit Sales, Konter Butet Celluler
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases
Divisions:	Fakultas Sains Dan Teknologi > Sistem Informasi
Depositing User:	Unnamed user with email repository@ulb.ac.id
Date Deposited:	21 Oct 2025 09:10
Last Modified:	21 Oct 2025 09:10
URI:	http://repository.ulb.ac.id/id/eprint/1829

Actions (login required)

View Item