Machine Learning-Driven Customer Segmentation and Targeted Marketing: A Systematic Reviews

Main Article Content

Lahcen Abidar, Ikran EL Asri, Dounia Zaidouni, Abdeslam Ennouaary

Abstract

Customer segmentation is a cornerstone of marketing strategy, enabling businesses to gain valuable insights into the needs, preferences, and behaviors of their customers. Machine learning has emerged as a powerful tool for customer segmentation, leveraging advanced algorithms to group customers based on shared characteristics and behavioral patterns.


This study presents a systematic review of 82 research papers published over the past decade that utilize statistical, machine learning, and deep learning techniques for customer segmentation. We propose a comprehensive categorization methodology for machine learning-driven segmentation algorithms and address key challenges, including data quality and availability, algorithm selection, feature engineering, business context alignment, and ethical and legal considerations.


Our finding several that machine learning algorithms are extensively employed across various industries, particularly retail, banking, and tourism. While deep learning techniques demonstrate superior accuracy in segmentation performance, machine learning methods remain more commonly adopted due to their balance of effectiveness and practicality.


We also analyze and compare widely used techniques, summarizing key datasets and proposed models in a structured format. This research highlights the significant benefits of machine learning-driven customer segmentation for both businesses and customers, offering actionable insights for its effective implementation.

Article Details

Section
Articles