{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-ensemble-based-approach-to-click-through","title":"An Ensemble-based Approach to Click-Through Rate Prediction for Promoted Listings at Etsy","arxiv_id":"1711.01377","date":"2017-11-04","proceeding":null,"authors":["Kamelia Aryafar","Devin Guillory","Liangjie Hong"],"abstract":"Etsy is a global marketplace where people across the world connect to make,\nbuy and sell unique goods. Sellers at Etsy can promote their product listings\nvia advertising campaigns similar to traditional sponsored search ads.\nClick-Through Rate (CTR) prediction is an integral part of online search\nadvertising systems where it is utilized as an input to auctions which\ndetermine the final ranking of promoted listings to a particular user for each\nquery. In this paper, we provide a holistic view of Etsy's promoted listings'\nCTR prediction system and propose an ensemble learning approach which is based\non historical or behavioral signals for older listings as well as content-based\nfeatures for new listings. We obtain representations from texts and images by\nutilizing state-of-the-art deep learning techniques and employ multimodal\nlearning to combine these different signals. We compare the system to\nnon-trivial baselines on a large-scale real world dataset from Etsy,\ndemonstrating the effectiveness of the model and strong correlations between\noffline experiments and online performance. The paper is also the first\ntechnical overview to this kind of product in e-commerce context.","url_abs":"http://arxiv.org/abs/1711.01377v2","url_pdf":"http://arxiv.org/pdf/1711.01377v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-ensemble-based-approach-to-click-through","repo_url":"https://github.com/cpapadimitriou/Click-Through-Rate-prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"an-ensemble-based-approach-to-click-through","repo_url":"https://github.com/imvishvaraj/ctr_nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"click-through-rate-prediction","task_name":"Click-Through Rate Prediction"},{"task_slug":"ensemble-learning","task_name":"Ensemble Learning"}],"methods":[{"method_slug":"1d-cnn","method_name":"1D CNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}