STUDY AND DEVELOPMENT OF MULTIMODAL MODELS TRAINED UNDER A SELF-SUPERVISED APPROACH TO ENHANCE SEARCH ENGINES, RECOMMENDATION SYSTEMS AND CUSTOMER SEGMENTATION IN THE CONTEXT OF E-COMMERCE

This project focuses on developing self-supervised models that exploit the multimodal nature of eCommerce to improve search engines, recommendation systems and customer segmentation. The multimodal nature of eCommerce is represented not only by catalog products but also by user queries. We can even find multimodal information related to products or trends in social media posts. From an architectural point of view, the proposed models will evaluate the use of self-attention and cross-attention modules to improve multimodal data representations.