STM Journals Peer-reviewed research from Consortium e-Learning Network

E-Commerce for Future & Trends Original Research

A Privacy-Preserving and Performance-Optimized Machine Learning Framework for Personalized E-Commerce User Experience

  1. Ravi Bhushan Kumar Department of Computer Science and Engineering, Suresh Gyan Vihar University
  2. Manish Sharma Department of Computer Science and Engineering, Suresh Gyan Vihar University

Abstract

In contemporary e-commerce websites, merchant suggestions are the most outstanding way to boost customer satisfaction and conversion levels. Nevertheless, the growing dependence on user data provokes significant concerns over the protection of privacy and efficiency in computation. In this paper, we have suggested a privacy-preserving and performance-optimized machine learning framework that allows customized e-commerce experiences and protects the sensitive information of users. The framework incorporates the concepts of federated learning with differential privacy to make sure that any personal data is decentralized and anonymized during the learning process. Additionally, there is a performance-optimization module that utilizes adaptive model compression and distributed training techniques to decrease latency and resource use without affecting accuracy. Real-world-scale e-commerce datasets were experimented with to compare the proposed model (FedEcom) with the traditional non-privacy baselines and differential privacy baselines. The findings indicate that FedEcom outperforms the baseline, achieving 93% accuracy and an AUC of 0.94, while reducing privacy leakage by 1.2% and training time by 10%. User experience surveys demonstrate that the framework has increased the click-through (7.5%), satisfaction (4.6/5), and conversion rate (3.9%) significantly, proving the efficiency of the framework to provide a balance between personalization, privacy, and system efficiency. The proposed study points to a viable way forward to reliable, scalable, and user-friendly A.I.-based e-commerce sites.

Keywords

References (13)

  1. Mrhar K, Abik M. A deep learning framework for optimizing personalized online course recommendation and selection. Decis Anal J. 2025;16:100616. doi:10.1016/j.dajour.2025.100616.
  2. Yang Q, Liu Y, Chen T, Tong Y. Federated machine learning: Concept and applications. ACM Trans Intell Syst Technol. 2019;10(2):1-19. doi:10.1145/3298981.
  3. 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.
  4. Kanchan S, Jang JW, Yoon JY, Choi BJ. Efficient and privacy-preserving group signature for federated learning. Future Gener Comput Syst. 2023;147:93-106. doi:10.1016/j.future.2023.04.017.
  5. Ali W, Kumar R, Deng Z, Wang Y, Shao J. A federated learning approach for privacy protection in context-aware recommender systems. Comput J. 2021;64(7):1016-27. doi:10.1093/comjnl/bxab025.
  6. Tanuwidjaja HC, Choi R, Baek S, Kim K. Privacy-preserving deep learning on machine learning as a service: A comprehensive survey. IEEE Access. 2020;8:167425-47. doi:10.1109/ACCESS. 3023084.
  7. Asad M, Shaukat S, Javanmardi E, Nakazato J, Tsukada M. A comprehensive survey on privacy-preserving techniques in federated recommendation systems. Appl Sci (Basel). 2023;13:6201. doi:10.3390/app13106201.
  8. Pulido-Gaytan B, Tchernykh A, Cortés-Mendoza JM, Babenko M, Radchenko G, Avetisyan A, et al. Privacy-preserving neural networks with homomorphic encryption: Challenges and opportunities. Peer-to-Peer Netw Appl. 2021;14:1666-91. doi:10.1007/s12083-021-01076-8.
  9. Alshammari A, El Hindi K. Privacy-preserving deep learning framework based on restricted Boltzmann machines and instance reduction algorithms. Appl Sci (Basel). 2024;14(3):1224. doi:10.3390/app14031224.
  10. Aouedi O, Sacco A, Piamrat K, Marchetto G. Handling privacy-sensitive medical data with federated learning: Challenges and future directions. IEEE J Biomed Health Inform. 2023;27:790-803. doi:10.1109/JBHI.2022.3185673. PMID:35737624.
  11. Tan S, Knott B, Tian Y, Wu DJ. CryptGPU: Fast privacy-preserving machine learning on the GPU. In: 2021 IEEE Symposium on Security and Privacy (SP); 2021. p. 1021-38. doi:10.1109/ 2021.00098.
  12. Imran M, Yin H, Chen T, Nguyen QVH, Zhou A, Zheng K. ReFRS: Resource-efficient federated recommender system for dynamic and diversified user preferences. ACM Trans Inf Syst. 2023;41:1-30. doi:10.1145/3560486.
  13. Chronis C, Varlamis I, Himeur Y, Sayed AN, Al-Hasan TM, Nhlabatsi A, et al. A survey on the use of federated learning in privacy-preserving recommender systems. IEEE Open J Comput Soc. 2024;5:227-47. doi:10.1109/OJCS.2024.3396344.
Support