All Times ET
Keywords: Computer Vision, Machine Learning, E-Commerce, CTR
To address the complexity of content personalization at Etsy's marketplace, our proposed approach aims at learning visual representations of products and directly optimizing user interactions. In doing so, we assume that a users' aesthetic preferences can be learned implicitly through their online behavior. By leveraging metadata from our existing recommendations platform, we train image representations to predict relevant items. Such an approach is more flexible than existing baselines that use manually defined taxonomic categorizations. We use a pairwise ranking framework by adopting the Bayesian Personalized Ranking paradigm while building off of the CuratorNet approach of sampling positive and negative examples from the listing page. Additionally, we adopt an adaptive sampling approach that separately draws from both impressions and the listing population distribution at large. We discuss these contributions and their implications for an online system that is evaluated on the basis of generated revenue.