{"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/deep-character-level-click-through-rate","title":"Deep Character-Level Click-Through Rate Prediction for Sponsored Search","arxiv_id":"1707.02158","date":"2017-07-07","proceeding":null,"authors":["Bora Edizel","Amin Mantrach","Xiao Bai"],"abstract":"Predicting the click-through rate of an advertisement is a critical component\nof online advertising platforms. In sponsored search, the click-through rate\nestimates the probability that a displayed advertisement is clicked by a user\nafter she submits a query to the search engine. Commercial search engines\ntypically rely on machine learning models trained with a large number of\nfeatures to make such predictions. This is inevitably requires a lot of\nengineering efforts to define, compute, and select the appropriate features. In\nthis paper, we propose two novel approaches (one working at character level and\nthe other working at word level) that use deep convolutional neural networks to\npredict the click-through rate of a query-advertisement pair. Specially, the\nproposed architectures only consider the textual content appearing in a\nquery-advertisement pair as input, and produce as output a click-through rate\nprediction. By comparing the character-level model with the word-level model,\nwe show that language representation can be learnt from scratch at character\nlevel when trained on enough data. Through extensive experiments using billions\nof query-advertisement pairs of a popular commercial search engine, we\ndemonstrate that both approaches significantly outperform a baseline model\nbuilt on well-selected text features and a state-of-the-art word2vec-based\napproach. Finally, by combining the predictions of the deep models introduced\nin this study with the prediction of the model in production of the same\ncommercial search engine, we significantly improve the accuracy and the\ncalibration of the click-through rate prediction of the production system.","url_abs":"http://arxiv.org/abs/1707.02158v1","url_pdf":"http://arxiv.org/pdf/1707.02158v1.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":"deep-character-level-click-through-rate","repo_url":"https://github.com/yrbahn/deep_match_ctr_prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"click-through-rate-prediction","task_name":"Click-Through Rate Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}