Analysis of customer shopping behavior on E-commerce platform supported by fuzzy clustering algorithm

Abstract The optimization of customers’ purchasing experiences and the enhancement of e-commerce platform revenue can be achieved through the analysis of consumers’ online shopping behavior. When it comes to capturing the intricacy and fluidity of consumer actions, traditional clustering algorithms frequently struggle to do so. Fuzzy clustering algorithms address some of these issues; nevertheless, these algorithms are unable to react effectively to changing client behaviors. In this study, a novel framework known as Adaptive Fuzzy Clustering for Behavioral Segmentation (AFCBS) is proposed. This framework is designed to address the limitations that are associated with traditional clustering algorithms. By taking into account browsing patterns, transaction history, and product preferences, AFCBS is able to more precisely segment customers. This is accomplished while simultaneously managing noise and outliers in expansive datasets. It includes adaptive processes to ensure that clusters evolve in response to changing behaviors over time and allows customers to belong to various segments with varying degrees of membership. Additionally, it allows consumers to join multiple segments. By taking this technique, exact client segments are generated, which provides insights that may be used for personalized advice, focused marketing, and improved company strategies. Providing a thorough framework for understanding consumer demands, optimizing marketing efforts, and enhancing e-commerce success, the results reveal that AFCBS improves segmentation accuracy, customer engagement, satisfaction, and retention. Additionally, it provides a stronger framework for retaining customers.