Sistem Rekomendasi Berdasarkan Kolaborasi antara Dimensi Merek dan Produk dengan Menggunakan Sistem Pakar Fuzzy

Husnah, Mirdatul (2023) Sistem Rekomendasi Berdasarkan Kolaborasi antara Dimensi Merek dan Produk dengan Menggunakan Sistem Pakar Fuzzy. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6026212006-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 September 2025. Download (2MB) | Request a copy

Abstract

Perkembangan teknologi saat ini telah banyak mendorong perubahan dalam peta bisnis perusahaan. Sehingga banyak perusahaan yang kini mulai berfokus kepada manajemen hubungan dengan pelanggan melalui analisis pengetahuan mengenai pelanggan berdasarkan data historis transaksi pelanggan. Namun, hal ini sering kali menyebabkan perspektif lama yaitu perspektif produk/merek cenderung dilupakan oleh perusahaan. Oleh karena itu, penelitian ini menggabungkan perspektif pelanggan, perspektif merek dan produk menggunakan model LRFM/B yaitu length, recency, frequency, monetary/brand dan LRFM/P yaitu length recency frequency, monetary/product. Dengan mengintegrasikan kedua perspektif tersebut, menjadikan perusahaan tidak perlu meninggalkan salah satu perspektif, sehingga dapat memudahkan perusahaan dalam mengelola pelanggan sesuai dengan segmentasi pelanggan berdasarkan loyalitasnya pada produk atau merek tersebut. Selain itu, penelitian ini akan memberikan rekomendasi produk dan merek untuk membantu mendukung keputusan pembelian pelanggan. Clustering dilakukan dengan fuzzy c-means berdasarkan dimensi LRFM/B dan LRFM/P. Kemudian hasil dari clustering akan menjadi input bagi rekomendasi collaborative filtering. Keluaran collaborative filtering akan memberikan input bagi fuzzy expert system yaitu nilai rating dan kesamaan. Kemudian fuzzy expert system akan memberikan keluaran berupa nilai kepentingan rekomendasi kepada pelanggan. Kemudian, hasil uji kualitas rekomendasi memperoleh nilai ketepatan 92% hingga 100%. Dengan demikian, rekomendasi ini merupakan rekomendasi yang dapat diterima oleh pelanggan dan menjadi peluang bagi perusahaan.
================================================================================================================================
Current technological developments have driven many changes in the company's business plan. So many companies are now starting to focus on customer relationship management through analysis of customer knowledge based on historical customer transaction data. However, this often causes old perspectives, namely product and brand perspectives, to be forgotten by companies. Therefore, this study combines customer perspectives, brand perspectives, and product perspectives using the LRFM/B model, namely length, recency, frequency, monetary/brand, and the LRFM/P model, namely length, recency, frequency, monetary/product. By integrating these two perspectives, the company does not need to leave one perspective, so it can make it easier for companies to manage customers according to customer segmentation based on loyalty to the product or brand. In addition, this research will provide product and brand recommendations to help support customer purchasing decisions. Clustering is done with fuzzy c-means based on LRFM/B and LRFM/P dimensions. Then the results of clustering will be input for collaborative filtering recommendations. The output of collaborative filtering will provide input for the fuzzy expert system, namely rating and similarity values. Then the fuzzy expert system will provide output in the form of a recommendation of importance to the customer. Then, the results of the recommendation quality test obtained an accuracy value of 92% to 100%. Thus, this recommendation is one that can be accepted by customers and becomes an opportunity for the company.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	customer segmentation, LRFM, brand, product, recommendation system, fuzzy c-means, collaborative filtering, fuzzy expert system, segmentasi pelanggan, LRFM, merek, produk, sistem rekomendasi, fuzzy c-means, collaborative filtering, fuzzy expert system
Subjects:	Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) Q Science > QA Mathematics > QA76.9.I58 Recommender systems (Information filtering)
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 59101-(S2) Master Thesis
Depositing User:	Mirdatul Husnah
Date Deposited:	26 Jul 2023 08:47
Last Modified:	26 Jul 2023 08:47
URI:	http://repository.its.ac.id/id/eprint/99242

Actions (login required)

View Item