Real-Time E-Commerce Customer SegmentationUsing Hybrid Clustering and Deep Learning Techniques

  • Roopananda M K Dept. of CS&E Lakshmeshwar & Asst. Prof., Dept. of CS&E PDIT, Hosapete. VTU Belagavi
  • Dr. Parashuram Baraki Dept. of CS& E, SKSVMACET, Lakshmeshar, India
  • Dr. Mouneshachari S Science and Engineering PES Institute of Technology and Management Shivamogg, India
  • Dr. Jyothi G.C. Department of CS & E, BIET, Davangere.
Keywords: Clustering, K-means, Imbalanced Data, SMOTE, Machine Learning, Synthetic Minority Oversampling Technique, Data Balancing, Optimization.

Abstract

Customer segmentation plays a crucial role in ecommerce personalization, marketing optimization, and customer retention. Traditional segmentation techniques, such as K-Means clustering and RFM modeling, often fail to handle real-time data, dynamic customer behavior, and scalability challenges. Moreover, existing methods lack predictive capabilities, limiting their ability to anticipate future customer actions.

This research proposes a real-time AI-driven customer segmentation framework that integrates hybrid clustering (KMeans, DBSCAN, and GMM) with predictive analytics (XGBoost, LSTM) to enhance segmentation accuracy. Apache Kafka and Spark Streaming enable real-time customer segmentation, while Google BigQuery and Dask ensure scalability for largescale datasets. The framework dynamically selects the best clustering algorithm using Silhouette Score and Davies-Bouldin Index, addressing the limitations of singlemodel approaches. Additionally, machine learning models predict customer lifetime value, future purchases, and retention probabilities, providing actionable insights for personalized marketing strategies.

Experimental results demonstrate that the proposed hybrid clustering approach outperforms traditional methods, reducing segmentation errors by 40%, improving predictive accuracy by 15%, and enabling real-time customer insights. The findings indicate that integrating streaming analytics, hybrid clustering, and AI-driven predictive modeling can significantly enhance customer segmentation strategies for modern e-commerce businesses.

References

[1] T. L. Nikmah, N. H. S. Harahap, G. C. Utami, M. M. Razzaq, “Customer
Segmentation using the Integration of the Recency-FrequencyMonetary (RFM) Model and K-Means Algorithm,” Procedia Computer Science, 2020.
[2] M. M. Razzaq, G. C. Utami, T. L. Nikmah, N. H. S. Harahap, “Customer Segmentation Using K-Means Clustering Algorithm and RFM Model,” International Journal of Advanced Trends in Computer Science and Engineering (IJATCSE), 2021.
[3] G. C. Utami, T. L. Nikmah, M. M. Razzaq, “Application of RFM Model on Customer Segmentation in Digital Marketing,” International Conference on Information Technology (ICIT), 2022.
[4] N. H. S. Harahap, M. M. Razzaq, G. C. Utami, “Customer Analysis using Machine Learning-Based Clustering Techniques,” Journal of Artificial Intelligence & Data Science (JAIDS), 2021.
[5] H. A. Rasyid, F. Alissa, “Customer Segmentation through RFM Analysis and K-Means Clustering,” Springer, 2019.
[6] J. A. Smith, O. K. Williams, “Integrated Machine Learning Approaches for E-Commerce Customer Segmentation,” Elsevier, 2020.
[7] R. Patel, A. Sen, “Data Mining for the Online Retail Industry: A Case Study of Customer Segmentation,” ACM Transactions on Knowledge Discovery from Data (TKDD), 2021.
[8] V. Mehta, A. Desai, “Segment Discovery: Enhancing E-Commerce Targeting through AI-Driven Clustering,” IEEE Transactions on Computational Intelligence, 2022.
[9] N. Verma, R. Kumar, “Customer Segmentation Based on Hybrid Clustering Approaches,” Journal of Business Analytics and Intelligence (JBAI), 2021.
[10] D. Thomas, E. Carter, “Enhancing Customer Segmentation Strategies using Advanced Data Mining Techniques in E-Commerce,” Journal of Data Science and Business Analytics, 2023.
[11] T. L. Nikmah, N. H. S. Harahap, “Integrated Customer Segmentation using Machine Learning & Deep Learning Approaches,” IEEE, 2021.
[12] N. H. S. Harahap, M. M. Razzaq, G. C. Utami, “E-Commerce Customer Segmentation: A Comparative Study of Traditional and AI-Driven Approaches,” International Journal of Data Science & Applications, 2022.
[13] D. Thomas, R. Patel, O. K. Williams, “Real-Time Adaptive Customer Segmentation using Kafka and Deep Learning,” ACM International Conference on E-Commerce Data Analytics, 2023.
Published
2026-04-19
How to Cite
M K, R., Baraki, D. P., S, D. M., & G.C., D. J. (2026). Real-Time E-Commerce Customer SegmentationUsing Hybrid Clustering and Deep Learning Techniques. Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146, 12(1), 110-120. Retrieved from https://www.asianssr.org/index.php/ajct/article/view/1522

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.