SAMSUL, SAMSUL (2022) PERBANDINGAN KINERJA FUZZY C-MEANS DENGAN DBSCAN UNTUK MENENTUKAN SEGMENTASI PELANGGAN BERDASARKAN RFM STUDI KASUS PRINTO DIGITAL PRINTING. S1 thesis, Universitas Mercu Buana.
|
Text (HAL COVER)
01 Cover.pdf Download (1MB) | Preview |
|
|
Text (ABSTRAK)
02 Abstrak.pdf Download (116kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
03 Bab 1.pdf Restricted to Registered users only Download (211kB) |
|
|
Text (BAB II)
04 Bab 2.pdf Restricted to Registered users only Download (65kB) |
|
|
Text (BAB III)
05 Bab 3.pdf Restricted to Registered users only Download (193kB) |
|
|
Text (BAB IV)
06 Bab 4.pdf Restricted to Registered users only Download (98kB) |
|
|
Text (BAB V)
07 Bab 5.pdf Restricted to Registered users only Download (488kB) |
|
|
Text (BAB VI)
08 Bab 6.pdf Restricted to Registered users only Download (52kB) |
|
|
Text (DAFTAR PUSTAKA)
09 Daftar Pustaka.pdf Restricted to Registered users only Download (156kB) |
|
|
Text (LAMPIRAN)
10 Lampiran.pdf Restricted to Registered users only Download (329kB) |
Abstract
The impact of Covid-19 is being felt by companies, for instance the reduced sales due to Large-Scale Social Restrictions (PSBB). Customer’s loyalty is vital for every company in order to continue to grow and develop. Thus, the competition for each company is increasing, both through marketing strategies, product quality, and services. One of the goals of the competition is customer’s loyalty. By grouping several customer patterns, it is expected to see the level of customer loyalty. Therefore, it could determine sufficient and effective marketing strategy for each customer group. However, with many algorithms and approaches that could be used in customer clustering, the researchers compared the Fuzzy C-Means algorithm as a representative of the partition approach and the DBSCAN algorithm as a representative of the density approach to determine which algorithm and approach are more suitable.. The researcher uses a dataset derived from a Printo salesman's transactions from January 04, 2021 to December 31, 2021, with a total of 2258 transactions from 614 customers and using RFM score method (Recency, Frequency, and Monetary), the determination of the number of clusters is measured using the Davies-Bouldin Index score and produces 3 clusters. The cluster will be validated with several algorithms. The Silhouette Index validation with the FCM score of 0.67 and DBSCAN of 0.616, on the validation of the Calinski Harabasz Score or commonly called the Variance Ratio Criterion with the FCM score of 698.74 and DBSCAN of 149.79, on the DBCV validation with the FCM score of -0.92 while the results of cluster validation using the DBSCAN algorithm were -0.64. FCM is chosen as the preferred algorithm for the Printo sales dataset the 2021 period, then the average RFM value will be multiplied by the RFM weight value that has been approved by the decision maker, which is 0.25 (R), 0.35 (F), 0.4 (M) which will result in the ranking of each Customer Life Value (CLV) cluster. The highest-ranking cluster is cluster 1 with a CLV score of 3.325.. Key words: Fuzzy C-Means, DBSCAN, RFM, CLV Dampak Covid-19 sangat dirasakan bagi setiap perusahaan, berkurangnya penjualan dikarenakan Pembatasan Sosial Berskala Besar (PSBB), loyalitas pelanggan sangat dibutuhkan bagi setiap perusahaan agar tetap dapat tumbuh dan berkembang. Sehingga kompetisi setiap perusahaan semakin meningkat, baik melalui strategi pemasaran, kualitas produk, maupun pelayanan. Salah satu tujuan dari kompetisi tersebut adalah loyalitas pelanggan. Dengan mengelompokan beberapa pola pelanggan diharapkan dapat melihat tingkat loyalitas pelanggan. Sehingga dapat menentukan strategi pemasaran yang tepat dan efektif bagi setiap kelompok pelanggan. Namun banyaknya algoritma dan pendekatan yang dapat digunakan dalam pengelompokan pelanggan, peneliti membandingkan algoritma Fuzzy C-Means sebagai perwakilan dari pendekatan partisi dan algoritma DBSCAN sebagai perwakilan dari pendekatan kepadatan untuk menentukan algoritma dan pendekatan yang lebih tepat, Peneliti menggunakan dataset yang berasal dari transaksi seorang salesman Printo selama 04 Januari 2021 – 31 Desember 2021, dengan total 2258 transaksi dari 614 pelanggan dan menggunakan metode skor RFM ( Recency, Frequency, dan Monetary ), penentuan jumlah cluster diukur menggunakan skor Davies-Bouldin Index dan menghasilkan 3 cluster, cluster akan divalidasi dengan beberapa algoritma, pada validasi Silhouette Index dengan hasil skor FCM sebesar 0.6658317555663252 dan DBSCAN sebesar 0.6129409398826126, pada validasi Calinski-Harabasz Index atau biasa disebut dengan Variance Ratio Criterion dengan hasil skor FCM sebesar 698.7383292333917 dan DBSCAN sebesar 149.7867851728282, pada validasi DBCV dengan hasil skor FCM adalah sebesar -0.9186050826327292 sedangkan hasil pada validasi cluster menggunakan algoritma DBSCAN adalah sebesar -0.6410032125143688. FCM dipilih sebagai skema algoritma terbaik untuk dataset penjualan Printo periode tahun 2021, selanjutnya rata-rata nilai RFM akan dikalikan dengan nilai bobot RFM yang telah disetujui oleh pengambil keputusan yaitu sebesar 0.25 (R), 0.35 (F), 0.4 (M) yang akan menghasilkan peringkat setiap cluster Customer Life Value (CLV). Peringkat tertinggi cluster adalah cluster 1 dengan skor CLV sebesar 3.325. Kata kunci: Fuzzy C-Means, DBSCAN, RFM, CLV
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/INFO. 22 122 |
| Call Number: | SIK/15/22/047 |
| NIM/NIDN Creators: | 41518110232 |
| Uncontrolled Keywords: | Fuzzy C-Means, DBSCAN, RFM, CLV |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika 600 Technology/Teknologi > 630 Agriculture and Related Technologies/Pertanian dan Teknologi Terkait |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | WADINDA ROSADI |
| Date Deposited: | 19 Oct 2022 07:56 |
| Last Modified: | 19 Oct 2022 07:56 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/70612 |
Actions (login required)
 |
View Item |
