Adaptive and Explainable ML Framework for Personalized E-Commerce User Experience and Satisfaction

Year : 2026 | Volume : 16 | Issue : 02 | Page : 23 32
By

Ravi Bhushan Kumar,

Manish Sharma,

  1. Research Scholar, Department of Computer Science and Engineering, Suresh Gyan Vihar University, Rajasthan, India
  2. Professor, Department of Computer Science and Engineering, Suresh Gyan Vihar University, Rajasthan, India

Abstract

The user experience and user satisfaction have taken the center of the stage as a determinant of platform success in the fast-changing e-commerce ecosystem. Conventional recommendation systems are usually run in black-box models that give minimal transparency and dynamicity to altered user preferences. The study will introduce a personalization framework of explainable machine learning (XML) based on explainable artificial intelligence (XAI) and hybrid recommendation strategies. The model uses Collaborative Filtering (CF), Content-Based Filtering (CBF), and Deep Neural Networks (DNNs) to identify explicit and implicit user behaviors, whereas Shapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) can make recommendations more interpretable and transparent. Experimental tests show that the suggested framework is more effective in terms of achieving high performance rates of 94.65, F1-score of 93.68, and a lower RMSE of 0.284; which is better than standard models. In addition, the indicators of user engagement include session duration, the number of clicks, and satisfaction scores, which significantly improve. Muhammad explored the use of adaptive learning and explainability to improve the accuracy of personalization, as well as to provide greater user trust, which, in turn, results in a clearer, more trustworthy, more user-oriented e-business experience.

Keywords: Personalization, explainable artificial intelligence, hybrid recommendation system, adaptive machine learning, user engagement

[This article belongs to Current Trends in Information Technology ]

How to cite this article: Ravi Bhushan Kumar, Manish Sharma. Adaptive and Explainable ML Framework for Personalized E-Commerce User Experience and Satisfaction. Current Trends in Information Technology. 2026; 16(02):23-32.
How to cite this URL: Ravi Bhushan Kumar, Manish Sharma. Adaptive and Explainable ML Framework for Personalized E-Commerce User Experience and Satisfaction. Current Trends in Information Technology. 2026; 16(02):23-32. Available from: https://journals.stmjournals.com/ctit/article=2026/view=258962

References

  1. Kaponis A, Maragoudakis M, Sofianos KC. Enhancing user experiences in digital marketing through machine learning: cases, trends, and challenges. Computers (Basel). 2025;14:211. doi:10.3390/computers14060211.
  2. Almahmood RJK, Tekerek A. Issues and solutions in deep learning-enabled recommendation systems within the e-commerce field. Appl Sci (Basel). 2022;12:11256. doi:10.3390/app122111256.
  3. Rabby F, Chimhundu R, Hassan R. Blockchain technology transforms digital marketing by growing consumer trust. In: Idrees SM, Nowostawski M, editors. Transformations Through Blockchain Technology: The New Digital Revolution. Springer International Publishing; 2022. p. 265-89. doi:10.1007/978-3-030-93344-9_12.
  4. Wang P, Li K, Du Q, Wang J. Customer experience in AI-enabled products: scale development and validation. J Retail Consum Serv. 2024;76:103578. doi:10.1016/j.jretconser.2023.103578.
  5. Lu T, Zhou Z, Wang J, Wang Y. A large language model-based approach for personalized search results re-ranking in professional domains. Int J Lang Stud. 2024;1:1-6. doi:10.60087/ijls.v1.n2.001.
  6. Pal B. Personalization strategies in e-commerce: leveraging machine learning for enhanced customer experience. Acad Mark Stud J. 2024;28:1-26.
  7. Ekasari S, Judijanto L, Vandika AY. The role of artificial intelligence and machine learning in precision targeting: revolutionizing marketing strategies. Jurnal Ekonomi dan Bisnis. 2024;2:347-61.
  8. Ekasari S, Judijanto L, Vandika AY. The role of artificial intelligence and machine learning in precision targeting: revolutionizing marketing strategies. Jurnal Ekonomi dan Bisnis. 2024;2:347-61.
  9. Pereira AM, Moura JAB, Costa EDB, Vieira T, Landim ARDB, Bazaki E, et al. Customer models for artificial intelligence-based decision support in fashion online retail supply chains. Decis Support Syst. 2022;158:113795. doi:10.1016/j.dss.2022.113795.
  10. Alhijawi B, Kilani Y. A collaborative filtering recommender system using genetic algorithm. Inf Process Manag. 2020;57:102310. doi:10.1016/j.ipm.2020.102310.
  11. Das S, Behera RK, Kumar M, Rath SK. Real-time sentiment analysis of Twitter streaming data for stock prediction. Procedia Comput Sci. 2018;132:956-64. doi:10.1016/j.procs.2018.05.111.
  12. Yin J, Qiu X, Wang Y. The impact of AI-personalized recommendations on clicking intentions: evidence from Chinese e-commerce. J Theor Appl Electron Commer Res. 2025;20:21. doi:10.3390/jtaer20010021.
  13. Valencia-Arias A, Uribe-Bedoya H, González-Ruiz JD, Santos GS, Ramírez EC, Rojas EM. Artificial intelligence and recommender systems in e-commerce: trends and research agenda. Intell Syst Appl. 2024;24:200435. doi:10.1016/j.iswa.2024.200435.
  14. Huang S, Diao S, Zhao H, Xu L. The contribution of federated learning to AI development. In: The 24th International Scientific and Practical Conference “Technologies of Scientists and Implementation of Modern Methods”; 2024 Jun 18. International Science Group; 2024. p. 358.
  15. Carole KS, Theodore Armand TP, Kim HC. Enhanced experiences: benefits of AI-powered recommendation systems. In: Proceedings of the 26th International Conference on Advanced Communications Technology (ICACT); 2024. Institute of Electrical and Electronics Engineers; p. 216-20. doi:10.23919/ICACT60172.2024.10471918.
Regular Issue Subscription Original Research
Volume 16
Issue 02
Received 23/02/2026
Accepted 14/03/2026
Published 05/04/2026
Publication Time 41 Days

Login

My IP

PlumX Metrics

Support