Answers are grounded in this paper and cite their sources.
In present day data driven marketing process customer segmentation is very important component so that institutions may understand diverse client behavior and undertake design inspired initiatives. With growing availability of transactional data, artificial intelligence (AI) -based unsupervised learning techniques have gained popularity for identifying meaningful customer segments without prior labeling. This study presents a comparative analysis of three commonly used approaches to customer segmentation such as K-Means clustering, Hierarchical clustering, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). This study is based on the data set taken from Kaggle consisting of 541,909 records and eight variables. The customer label data which is aggregated from transaction-level to construct behavioral features based on Recency, Frequency, and Monetary (RFM). Along with additional purchase behavior indicator to assess transaction and principal component analysis (PCA) was applied prior to clustering for high scale sensitivity and high dimensionality. Study results showed that K-Means offer well separated stable clusters of large customer groups. Hierarchical clustering offers valuable insights into cluster structures and DBSCAN nicely diagnosed noise and atypical purchasing behavior at the same time sensitive to parameter selection in high density marketing data. The study showcased the trade-offs between algorithmic performance as well as business interpretability, giving guidance to marketing analysts enabling decision-makers to decide suitable segmentation techniques.
No takes yet. Share an insight, caveat, or question.
Bhardwaj et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: