Zobrazit v EDS

Customer Segmentation Using the K-Means Algorithm for Marketing Strategy Design: Case Study at the Icon Yasika Makassar

Uloženo v:
Podrobná bibliografie
Název: Customer Segmentation Using the K-Means Algorithm for Marketing Strategy Design: Case Study at the Icon Yasika Makassar
Autoři: Maulana Rumi Irwan Balo, Muhammad Rakib, Muhammad Ashdaq
Zdroj: International Journal of Innovative Science and Research Technology. :1041-1047
Informace o vydavateli: International Journal of Innovative Science and Research Technology, 2025.
Rok vydání: 2025
Popis: This research aims to segment customers of the Icon Yasika Makassar by implementing the K-Means clustering algorithm using the LRFM (Length, Recency, Frequency, Monetary) model. The purpose is to group customers based on their transaction behavior to develop targeted and data-driven marketing strategies. Using transaction data from February 2022 to June 2023, the study processed LRFM scores for each customer and applied K-Means clustering with Elbow and Davies-Bouldin Index methods to determine the optimal number of clusters. The results identified five distinct customer segments with varying characteristics, such as lost customers, core customers, and new customers. A dashboard was developed to visualize segmentation insights and support strategic marketing decisions. This study supports the application of Business Intelligence and behavioral segmentation in improving customer understanding and enhancing digital marketing effectiveness.
Druh dokumentu: Article
Jazyk: English
DOI: 10.38124/ijisrt/25jul508
Přístupové číslo: edsair.doi...........e598e8872d4e4f3d928de35ffc23b446
Databáze: OpenAIRE
Popis
Abstrakt:This research aims to segment customers of the Icon Yasika Makassar by implementing the K-Means clustering algorithm using the LRFM (Length, Recency, Frequency, Monetary) model. The purpose is to group customers based on their transaction behavior to develop targeted and data-driven marketing strategies. Using transaction data from February 2022 to June 2023, the study processed LRFM scores for each customer and applied K-Means clustering with Elbow and Davies-Bouldin Index methods to determine the optimal number of clusters. The results identified five distinct customer segments with varying characteristics, such as lost customers, core customers, and new customers. A dashboard was developed to visualize segmentation insights and support strategic marketing decisions. This study supports the application of Business Intelligence and behavioral segmentation in improving customer understanding and enhancing digital marketing effectiveness.
DOI:10.38124/ijisrt/25jul508