A Hybrid Approach to Optimize Market Segmentation: Integration of Unsupervised Clustering and Supervised Ensemble Method

DOI

10.2991/978-94-6463-787-8_37How to use a DOI?

Keywords

Market Segmentation; Customer Segmentation; Customer Clustering; Ensemble Learning; XGBoost; Gaussian Mixture Model (GMM); Principal Component Analysis (PCA); t-SNE

Abstract

Market segmentation is critical process in comprehending customer diversity and customizing marketing techniques for better business outcomes. Using ensembled method upon real time dataset, this research work is presenting a robust framework for market segmentation. The main aim is to search for meaningful and significant customer clusters and correctly classify them so that companies could be enable or implement their marketing and resource allocation practices. The primary dataset collected is comprised of multi-dimensional features, behavioral, and psychographic attributes. At beginning, encoding categorical features, normalization of numerical values using dimensionality reduction such as Principal Component Analysis (PCA) and t-SNE (t-Distributed Stochastic Neighbor Embedding) for feature simplification process are deployed. Clustering is being performed by using Gaussian Mixture Model (GMM) and Silhouette score was useful to optimize cluster numbers and covariance type. For effective allocation of customers to identified segments, a classification model based on ensembled learning method such as XGBoost over primary dataset is being trained by using post clustering. To assess the performance of model, various metrics such as: classification accuracy, silhouette score and visual cluster validation is calculated. Results of research work demonstrates accurate and precise classification system with improved interpretability of customer behavior and presents significant insights for market segmentation. The discussed method ensures scalability and adaptability by integrating unsupervised clustering with supervised ensemble classification which eventually increases the market segmentation. This research framework helps businesses understand their customers better, thereby targeting the right marketing and proper resource allocation. It has shown a high accuracy of 99.75% and identifies customer segments very effectively (silhouette score: 0.6172).

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sakshi Dua
AU  - Devender Kumar
AU  - Sonu Dua
AU  - Jyoti Batra
PY  - 2025
DA  - 2025/07/17
TI  - A Hybrid Approach to Optimize Market Segmentation: Integration of Unsupervised Clustering and Supervised Ensemble Method
BT  - Proceedings of the Recent Advances in Artificial Intelligence for Sustainable Development (RAISD 2025)
PB  - Atlantis Press
SP  - 474
EP  - 483
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-787-8_37
DO  - 10.2991/978-94-6463-787-8_37
ID  - Dua2025
ER  -