Ariyo W,, Frans Dito (2025) CUSTOMER BEHAVIOR SEGMENTATION ANALYSIS IN THE E-COMMERCE INDUSTRY USING THE FUZZY C-MEANS CLUSTERING METHOD. Skripsi thesis, Universitas Pakuan.
Full text not available from this repository.Abstract
CUSTOMER BEHAVIOR SEGMENTATION ANALYSIS IN THE E-COMMERCE INDUSTRY USING THE FUZZY C-MEANS CLUSTERING METHOD Frans Dito Aryo Wibowo 1) , Aries Maesya 2) , Dinar Munggaran Akhmad 3) 1)2)3) Pakuan University, Pakuan University, Pakuan University, Indonesia Abstract Background: Indonesia's increasingly competitive economic conditions require companies to understand customer behavior patterns more accurately. In an era of tight business competition, companies are required to compete not only in products, but also in the ability to analyze customer data to develop long-term business and investment strategies. However, consumer behavior is complex and does not always match their statements or expectations, so a data-based analytical approach such as data mining is needed. Objective: This study aims to analyze customer behavior with a data mining approach to help companies recognize customer purchasing patterns more accurately. With a deeper understanding of consumer behavior, companies can group customers into specific segments and find patterns of relationships between products that are often purchased together. The results of this analysis are expected to be used as a basis for developing marketing strategies and making more targeted business decisions. Methods: The methods used in this study are Fuzzy C-Means Clustering (FCM) and FP-Growth. FCM is a fuzzy logicbased clustering technique that allows each data to have a degree of membership in more than one cluster, thus providing flexibility in customer grouping. While the FP-Growth algorithm is used to find frequent itemsets or item patterns that often appear together in customer transactions. FP-Growth works by building an FP-Tree data structure, which allows the pattern extraction process to be carried out efficiently without having to produce candidate combinations as in the Apriori algorithm. Results: Through the clustering process with FCM, customers are successfully grouped into several clusters based on similarities in purchasing behavior, such as transaction frequency, purchase amount, shopping value, and product preferences. Each cluster shows unique characteristics that can be utilized for different marketing approaches. In addition, the application of the FP-Growth algorithm produces association patterns between products, namely items that are often purchased together by customers, which can be used as a basis for building a product recommendation system or bundling offers. Conclusion: The results of the study show that the combination of Fuzzy C-Means and FP-Growth methods can provide a more comprehensive understanding of customer behavior. FCM is effective in grouping customers with a high level of flexibility, while FP-Growth is able to identify purchasing patterns that are useful for marketing strategies. Both methods provide important contributions in supporting smarter, adaptive, and data-driven business decision-making, especially in the face of increasingly competitive industry competition. Keywords: Analysis, Fuzzy C-Means Clustering (FCM), FP-Growth, Segmentation, Clustering.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Subjects: | Fakultas Ilmu Pengetahuan Alam dan Matematika > Ilmu Komputer |
| Divisions: | Fakultas Matematika dan Ilmu Pengetahuan Alam > Ilmu Komputer |
| Depositing User: | PERPUSTAKAAN FAKULTAS MATEMATIKA DAN ILMU PENGETAHUAN ALAM UNPAK |
| Date Deposited: | 21 Jun 2025 01:59 |
| Last Modified: | 21 Jun 2025 01:59 |
| URI: | http://eprints.unpak.ac.id/id/eprint/9680 |
Actions (login required)
 |
View Item |