With the rapid development of e-commerce and the increasing aging population, more elderly people are engaging in online shopping. However, challenges they face during this process are becoming more apparent. This article proposes a recommendation system based on click-through rate (CTR) prediction, aiming to enhance the online shopping experience for elderly users. By analyzing user characteristics, product features, and their interactions, we constructed a model combining bidirectional long short-term memory (Bi-LSTM) and multi-head self-attention mechanism to predict the item click behavior of elderly users in the recommendation section. Experimental results demonstrated that the model excels in CTR prediction, effectively improving the relevance of recommended content. Compared to the baseline model long short-term memory (LSTM), the GATI-RS framework improved CTR prediction accuracy by 40%, and its loss function rapidly decreased and remained stable during training. Additionally, the GATI-RS framework showed significant performance improvement when considering only elderly users, with accuracy surpassing the baseline model by 42%. These results indicate that the GATI-RS framework, through optimized algorithms, significantly enhances the model's global information integration and complex pattern recognition capabilities, providing strong support for developing recommendation systems for elderly online shoppers. This research not only offers new insights for e-commerce platforms to optimize services but also contributes to improving the quality of life and well-being of the elderly.
* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.