Penerapan Algoritma Fuxxy C-Means Clustering Dalam Segmentasi Pelanggan Dengan RFM Model Untuk Optimalisasi Strategi Pemasaran Pada Unicoo Coffee

Iqbal, Majid (2026) Penerapan Algoritma Fuxxy C-Means Clustering Dalam Segmentasi Pelanggan Dengan RFM Model Untuk Optimalisasi Strategi Pemasaran Pada Unicoo Coffee. S1 Teknik Informatika thesis, STMIK Widya Cipta Dharma.

[img] Text
2243126-S1-Teknik Informatika.pdf
Restricted to Repository staff only
Download (1MB) | Request a copy
[img] Text
2243126-S1-Jurnal.pdf
Download (343kB)

Abstract

Iqbal Imam Majid, 2026, Penerapan Algoritma Fuzzy C-Means Clustering Dalam Segmentasi Pelanggan Dengan RFM Model Untuk Optimalisasi Strategi Pemasaran Pada Unico Coffee. Skripsi Program Studi Teknik Informatika, Sekolah Tinggi Menejemen Informatika dan Komputer Widya Cipta Dharma. Pembimbing Utama Drs. Azahari, M.Kom, Pembimbing Pendamping Ahmad Abul Khair, S.Kom.,MT. Kata Kunci: Fuzzy C-Means Clustering, RFM Model, Segmentasi Pelanggan, Strategi Pemasaran, Kedai Kopi. Di era persaingan bisnis kedai kopi yang semakin kompetitif, mempertahankan pelanggan dan memahami perilaku konsumen menjadi kunci utama untuk keberlanjutan bisnis. Unico Coffee, sebagai salah satu pelaku bisnis di industri ini, menghadapi tantangan dalam merumuskan strategi pemasaran yang tepat sasaran karena kurangnya pemahaman mendalam mengenai karakteristik dan nilai pelanggan mereka. Penelitian ini bertujuan untuk mengelompokkan pelanggan Unico Coffee berdasarkan perilaku transaksi mereka guna merumuskan strategi pemasaran yang lebih optimal dan personal. Pendekatan yang digunakan dalam penelitian ini adalah segmentasi pelanggan menggunakan model Recency, Frequency, dan Monetary (RFM) yang dikombinasikan dengan algoritma Fuzzy C-Means (FCM) Clustering. Data yang digunakan merupakan data historis transaksi pelanggan Unico Coffee selama periode [Masukkan Periode Data, misal: Januari - Desember 2023]. Model RFM digunakan untuk mengekstraksi fitur perilaku pelanggan, sedangkan algoritma FCM diterapkan untuk mengelompokkan pelanggan ke dalam beberapa cluster berdasarkan tingkat keanggotaannya yang bersifat fuzzy, memungkinkan analisis yang lebih fleksibel dibandingkan clustering tradisional. Evaluasi hasil clustering dilakukan menggunakan [Masukkan Metode Evaluasi, misal: Partition Coefficient (PC) atau Xie-Beni Index] untuk menentukan jumlah cluster optimal. Hasil penelitian menunjukkan bahwa pelanggan Unico Coffee dapat dikelompokkan ke dalam 3 cluster optimal, yaitu: Pelanggan Loyal (Loyal Customers), Pelanggan Berpotensi (Potential Customers), dan Pelanggan Berisiko Hilang (At-Risk Customers). Setiap cluster memiliki karakteristik RFM yang unik dan membutuhkan penanganan yang berbeda. Berdasarkan profil masing-masing cluster, dirumuskan usulan strategi pemasaran yang spesifik, seperti program loyalitas khusus untuk cluster bernilai tinggi dan kampanye reaktivasi untuk cluster yang mulai pasif. Penerapan segmentasi dengan metode ini diharapkan dapat membantu manajemen Unico Coffee dalam mengoptimalkan alokasi sumber daya pemasaran, meningkatkan retensi pelanggan, dan pada akhirnya mendorong pertumbuhan pendapatan. ============================================================ Iqbal Imam Majid, 2026, Application of the Fuzzy C-Means Clustering Algorithm for Customer Segmentation Using the RFM Model to Optimize Marketing Strategies at Unico Coffee. Undergraduate Thesis, Informatics Engineering Study Program, Widya Cipta Dharma College of Informatics and Computer Management. Principal Supervisor: Drs. Azahari, M.Kom.; Co-Supervisor: Ahmad Abul Khair, S.Kom., M.T. Keywords: Fuzzy C-Means Clustering, RFM Model, Customer Segmentation, Marketing Strategy, Coffee Shop. In the increasingly competitive coffee shop industry, retaining customers and understanding consumer behavior are essential to business sustainability. Unico Coffee faces challenges in formulating targeted marketing strategies because customer characteristics and values have not yet been analyzed in depth. This study aims to segment Unico Coffee customers based on their transaction behavior and to formulate more effective and personalized marketing strategy recommendations. The study applies the Recency, Frequency, and Monetary (RFM) model combined with the Fuzzy C-Means (FCM) clustering algorithm. The data consist of historical customer transactions at Unico Coffee from January to December 2025. Transaction data are cleaned, transformed into RFM variables, selected according to relevant features, and normalized using min-max normalization. The normalized data are then processed using FCM, which assigns each customer a degree of membership in every cluster and therefore provides a more flexible representation than hard clustering. The method is implemented in a web-based system that supports manual transaction entry, CSV import, RFM calculation, clustering, visualization, recommendation generation, and CSV export. The results show that Unico Coffee customers can be grouped into three segments: Priority Customers, Potential Customers, and At-Risk Customers. Each segment has different RFM characteristics and therefore requires a different marketing approach. Priority Customers can be maintained through loyalty and reward programs, Potential Customers can be encouraged through bundling, points, and repeat-visit promotions, while At-Risk Customers can be targeted through reactivation offers and personalized messages. Black-box testing indicates that all tested system functions operate as expected. The resulting segmentation can support Unico Coffee in allocating marketing resources more efficiently, improving customer retention, and designing more targeted promotional strategies.

Item Type: Thesis (S1 Teknik Informatika)
Additional Information: Pembimbing 1 : Drs. Azahari, M.Kom Pembimbing 2 : Ahmad Abul Khair, S.Kom,MT
Uncontrolled Keywords: Fuzzy C-Means Clustering, RFM Model, Segmentasi Pelanggan, Strategi Pemasaran, Kedai Kopi.
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Teknik Informatika
Depositing User: Iqbal Imam Majid
Date Deposited: 07 Aug 2026 05:51
Last Modified: 07 Aug 2026 05:51
URI: http://repository.wicida.ac.id/id/eprint/6439

Actions (login required)

View Item View Item
wicida repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.