Scholarlink

The exponential growth of e-commerce necessitates personalized recommendation systems, especially in fashion domains, where visual attributes heavily influence consumer preferences. This study introduces an ensemble learning model combining five deep learning architectures MobileNet, DenseNet121, Xception, VGG16, and VGG19 to enhance the performance of fashion product recommendation systems. While individual CNN models demonstrated strong classification capabilities, the ensemble achieved superior results with an accuracy of 98.34%. This paper highlights specific challenges addressed by the ensemble, including computational efficiency and scalability, leveraging advanced techniques like feature aggregation and the Annoy index for fast similarity searches. These contributions underline the transformative potential of CNN-based ensemble learning in revolutionizing online fashion retail.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing Fashion Product Recommendations Through CNN-Based Ensemble Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Ch. Rajani,
  • Sireesha Moturi,
  • M. Koteswara Rao,
  • Ponnaganti Saiganesh,
  • Syed Khaja Moula,
  • Patan Karimulla Khan

摘要

The exponential growth of e-commerce necessitates personalized recommendation systems, especially in fashion domains, where visual attributes heavily influence consumer preferences. This study introduces an ensemble learning model combining five deep learning architectures MobileNet, DenseNet121, Xception, VGG16, and VGG19 to enhance the performance of fashion product recommendation systems. While individual CNN models demonstrated strong classification capabilities, the ensemble achieved superior results with an accuracy of 98.34%. This paper highlights specific challenges addressed by the ensemble, including computational efficiency and scalability, leveraging advanced techniques like feature aggregation and the Annoy index for fast similarity searches. These contributions underline the transformative potential of CNN-based ensemble learning in revolutionizing online fashion retail.