Role of Consumer IoT smart devices for safety and security of data privacy to enhance user experience of e-commerce

The rapid advancement of Consumer Internet of Things (CIoT) smart devices has significantly transformed the electronic-commerce (e-commerce) setting by enhancing user experiences through personalized, efficient, and intuitive interactions. In this article, we propose a new Dynamic Adam driven-Analytic Long Short-Term Memory (DA-ALSTM) to analyze how CIoT devices can influence and monitor customer interactions and personalization in e-commerce through real-time data collection. Min-Max Normalization is employed in all the CIoT data attributes to convert comparable scale, and then the extracting key behavioral components in the scaled data using Principal Component Analysis (PCA), the predictive DA-ALSTM model is used in CIoT smart devices using TensorFlow, ALSTM can predict future user preferences, recommend customized product recommendations, and improve user experience. The proposed method's better performance in traditional approaches such as evaluated matrices are accuracy (95.6%), precision (93.15%), user satisfaction (92.6%), response time (150 ms), and MSE (1.2). The result demonstrates the DA-ALSTM effectively forecasts user preferences improves e-commerce personalization and enhances product recommendation accuracy and user experience in the CIoT smart devices then accurately predicts e-commerce platform performance are most significantly influenced by purchase history, browsing behavior, CIoT device interaction data, product reviews and ratings, search queries, digital marketing engagement, device and platform preferences, discounts response, offers, and price sensitivity, time of interaction, loyalty, and membership status, user feedback and satisfaction scores.

Text 124487.pdf - Published Version Restricted to Repository staff only Download (886kB) Official URL or Download Paper: https://ieeexplore.ieee.org/document/11006888/

Actions (login required)

View Item