Enhancing Customer Segmentation Granularity with DEA-Driven Federated Convolutional Autoencoders: A Deep Learning Approach
Enhancing Customer Segmentation Granularity with DEA-Driven Federated Convolutional Autoencoders: A Deep Learning Approach |
||
 |
 |
|
| © 2025 by IJETT Journal | ||
| Volume-73 Issue-9 |
||
| Year of Publication : 2025 | ||
| Author : Pentareddy Ashalatha, G.Krishna Mohan | ||
| DOI : 10.14445/22315381/IJETT-V73I9P103 | ||
How to Cite?
Pentareddy Ashalatha, G.Krishna Mohan,"Enhancing Customer Segmentation Granularity with DEA-Driven Federated Convolutional Autoencoders: A Deep Learning Approach", International Journal of Engineering Trends and Technology, vol. 73, no. 9, pp.20-31, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I9P103
Abstract
In the fast-changing environment of data-driven business models, successful customer segmentation is critical for targeted marketing, resource allocation, and sustainable customer retention. Conventional segmentation techniques are based on centralized designs and simple clustering algorithms, which are not capable of coping with the high-dimensional, distributed, and privacy-constrained nature of contemporary customer data. This research overcomes these limitations by proposing a new framework that combines Federated Convolutional Autoencoders (FCA) with Data Envelopment Analysis (DEA) to improve segmentation granularity and interpretability in a privacy-friendly way. The main goal of this research is to propose a decentralized, smart segmentation model that not only discovers hidden behavioral patterns in distributed datasets but also analyzes the operational efficiency of each customer segment for strategic decision-making. The suggested FCA model learns compressed, non-redundant feature representations from local nodes with unsupervised convolutional autoencoders and federates them through learning protocols without sharing raw data, and DEA is subsequently used to quantify segment efficiency based on crucial input-output parameters. The model is tested with a synthetic customer dataset that mimics multi-regional consumer behavior, and the implementation is performed using TensorFlow and PyTorch for deep learning and Python-based linear programming software for DEA. Experimental results of 95% accuracy show that the proposed method generates more sophisticated and strategically useful segments than traditional methods. In summary, the combination of FCA and DEA provides a scalable, interpretable, and privacy-preserving answer to customer segmentation, providing the foundation for smart, actionable, and secure customer analytics in distributed data settings.
Keywords
Federated Learning, Convolutional Autoencoder, Customer Segmentation, Data Envelopment Analysis, Distributed Deep Learning.
References
[1] Marawan Omran, Khaled Hamza, and Sally Elghamrawy, “Advancing Customer Segmentation in Banking: Harnessing Machine Learning and H2O for Personalized Insights,” International Conference on Advanced Intelligent Systems and Informatics, Cairo, Egypt, pp. 246-256, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Hithakrith Parshetty, Lokesh Palimkar, and Rohith Emandi, Customer Targeting and Segmentation, Predictive Analytics and Generative AI for Data-Driven Marketing Strategies, Chapman and Hall/CRC, pp. 68-81, 2024.
[Google Scholar] [Publisher Link]
[3] P. Sudarsanam et al., “Customer Segmentation using Mini Batch K-Means Clustering Algorithm,” 2024 8th International Conference on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India, pp. 801-805, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Lew Sook Ling, and Claireta Tang Weiling, “Enhancing Segmentation: A Comparative Study of Clustering Methods,” IEEE Access, vol. 13, pp. 47418-47439, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Pilli Sri Durga, J.A. Paulson, and Marri Srinivasareddy, and others, “Customer Segmentation Analysis for Improving Sales Using Clustering,” International Journal of Science and Research Archive, vol. 9, no. 2, pp. 708-715, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Rizkita Bagus Perdhana, and Jerry Heikal, “Enhancing Customer Segmentation in Online Transportation Services: A Comprehensive Approach Using K-Means Clustering and RFM Model,” Indonesian Interdisciplinary Journal of Sharia Economics (IIJSE), vol. 7, no. 2, pp. 2849-2865, 2024.
[Google Scholar] [Publisher Link]
[7] Taqwa Hariguna, and Shih Chih Chen, “Customer Segmentation and Targeted Retail Pricing in Digital Advertising Using Gaussian Mixture Models for Maximizing Gross Income,” Journal of Digital Market and Digital Currency, vol. 1, no. 2, pp. 183-203, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Meena Singh et al., “Leveraging K-Means Clustering and Hierarchical Agglomerative Algorithms for Scalable AI-Driven Customer Segmentation,” Journal of AI ML Research, vol. 11, no. 7, pp. 1-23, 2022.
[Google Scholar] [Publisher Link]
[9] S. Manimozhi, D. Ruby, and K. Biruntha, “An Elegant Evaluation: Triangulating Clustering Methods for Customer Segmentation,” 2024 Second International Conference on Emerging Trends in Information Technology and Engineering (ICETITE), Vellore, India, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Md Abu Sufian Mozumder et al., “Optimizing Customer Segmentation in the Banking Sector: A Comparative Analysis of Machine Learning Algorithms,” Journal of Computer Science and Technology Studies, vol. 6, no. 4, pp. 1-7, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Qi Le et al., “Personalized Federated Recommender Systems with Private and Partially Federated Auto Encoders,” arXiv Preprint, pp. 1-7, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Jeen Mary John, Olamilekan Shobayo, and Bayode Ogunleye, “An Exploration of Clustering Algorithms for Customer Segmentation in the UK Retail Market,” Analytics, vol. 2, no. 4, pp. 809-823, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Miguel Alves Gomes, and Tobias Meisen, “A Review on Customer Segmentation Methods for Personalized Customer Targeting in E-Commerce Use Cases,” Information Systems and e-Business Management, vol. 21, no. 3, pp. 527-570, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Chenguang Wang, “Efficient Customer Segmentation in Digital Marketing Using Deep Learning with Swarm Intelligence Approach,” Information Processing & Management, vol. 59, no. 6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Amit Sharma, Neha Patel, and Rajesh Gupta, “Enhancing Customer Segmentation Through AI: Analyzing Clustering Algorithms and Deep Learning Techniques,” European Advanced AI Journal, vol. 11, no. 8, pp. 1-26, 2022.
[Google Scholar] [Publisher Link]
[16] Gehna Upreti, and Arul Kumar Natarajan, Leveraging Unsupervised Machine Learning to Optimize Customer Segmentation and Product Recommendations for Increased Retail Profits, Intersection of AI and Business Intelligence in Data-Driven Decision-Making, IGI Global, pp. 257-282, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Shalom Mariam Aeby, V. Vedhik Mohan Rao, and Nikhil Gupta, Customer Segmentation Techniques in Predictive Analytics and Generative AI for Data-Driven Marketing Strategies, Predictive Analytics and Generative AI for Data-Driven Marketing Strategies, Chapman and Hall/CRC, pp. 234-246, 2024.
[Publisher Link]
[18] Daqing Chen, “Online Retail,” UCI Machine Learning Repository, 2015.
[CrossRef] [Publisher Link]
[19] Lahcen Abidar et al., “Predicting Customer Segment Changes to Enhance Customer Retention: A Case Study for Online Retail using Machine Learning,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 14, no, 7, pp. 910-920, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Zne-Jung Lee et al., “Clustering and Classification Based on Distributed Automatic Feature Engineering for Customer Segmentation,” Symmetry, vol. 13, no. 9, pp. 1-14, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Gbeminiyi Falowo, “Development of a Machine Learning Model for Brand and Audience Segmentation Using Demographic Data,” Corpus Intellectual, vol. 3, no. 3, pp. 1-21, 2024.
[Publisher Link]