Understanding Compulsive Buying Patterns Through Customer Segmentation: A Cluster Analysis Approach

Abstract

The increasing digitalization of marketplaces has intensified impulsive and compulsive buying behaviors, driven by emotional triggers and personalized online environments. Consumers are now more prone to unplanned purchases due to algorithmic targeting and psychological reinforcement mechanisms. This study aims to identify distinct consumer segments based on behavioral and psychological dimensions to understand variations in compulsive buying tendencies. A quantitative, descriptive research design was adopted using secondary data from the Kaggle platform. The dataset included consumers and six key variables income, total spending, browsing time, loyalty points used, previous purchases, and satisfaction ratings. Data were standardized using the Z-score method, and K-Means clustering was applied in Microsoft Excel. Several iterations were tested, and a three-cluster solution was finalized based on interpretability and variance distribution. The analysis revealed three distinct consumer segments: Cluster 1 (36.1%) representing high-spending, emotionally driven buyers; Cluster 2 (31.9%) comprising rational and satisfaction-oriented shoppers; and Cluster 3 (32.0%) depicting balanced, loyalty-driven consumers. Cluster 1 exhibited the highest total spending (M = 924.8 USD) and browsing time (M = 38.1 min), while Cluster 2 showed the highest satisfaction (M = 4.3). These patterns confirm a behavioural continuum from impulsive to rational buying tendencies. The study establishes that accessible, Excel-based K-Means clustering effectively segments consumers by combining behavioural and psychological indicators. It contributes a replicable framework for understanding compulsive buying and offers practical guidance for ethical, data-informed marketing strategies in digital commerce.