Machine Learning Segment Customers Based on Their Reviews in E-Commerce Portals: A Fresh Inquiry

Abstract

Purpose: Customer segmentation is crucial yet challenging, especially in differential pricing. This study highlights the growing role of machine learning (ML) in analyzing vast data to uncover hidden patterns.
Methods: Online reviews including text and pictorial forms are explored in this study as the data set to newly developed machine learning model. With the proliferation of online reviews, authors will get a wealth of data that can be harnessed to perform customer segmentation using ML techniques. This research focuses on how ML techniques can be used to analyze reviews, including text classification, sentiment analysis and clustering algorithms.
Results: Sentiment analysis categorizes reviews as positive, negative, or neutral, while text classification sorts them by topics (e.g., product features, pricing). Clustering identifies distinct customer segments. ML automates large-scale review analysis, revealing customer preferences that manual methods might miss. This study also compares ML techniques to assess their suitability for marketing segmentation.
Conclusion: Leveraging ML for customer segmentation provides a competitive edge. Further research is needed to refine ML models, enabling businesses to optimize products, services, and marketing strategies for targeted customer needs.