Predicting customer loyalty in omnichannel retailing using purchase behavior, socio-cultural factors, and learning techniques

Shima Roosta, Seyed Jafar Sadjadi and Ahmad Makui

PLOS ONE, 2025, vol. 20, issue 8, 1-45

Abstract: In the competitive retail omnichannel market, customer loyalty is essential for maintaining market share and reducing the cost of acquiring new customers. Previous research has primarily focused on factors influencing customer loyalty, often in isolation, but this study goes beyond traditional approaches. The aim of this research is to fill significant gaps in current studies by integrating a more comprehensive set of variables that reflect the complex and dynamic nature of customer loyalty in a flexible omnichannel environment. The main innovation of this study lies in the use of new and comprehensive omnichannel data, which includes sales data across various platforms, socio-economic conditions, shopping cart behaviors, and customer sentiments. The proposed model utilizes a hybrid approach, incorporating BERT for sentiment analysis, reinforcement learning for behavior analysis, and fine-tuning for improved predictions. Additionally, graph-based models (GCN) and adaptive learning are employed to analyze trends and predict loyalty at both individual and neighborhood levels. This research provides an intelligent analytical framework for predicting customer loyalty in omnichannel retail environments, enhancing Customer Relationship Management (CRM) subsystems within Enterprise Information Systems (EIS). By optimizing decisions in areas such as pricing, inventory management, and personalized advertising, this study ultimately leads to improved customer retention and increased market competitiveness.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0330338 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 30338&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0330338

DOI: 10.1371/journal.pone.0330338

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().