{"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/product-based-neural-networks-for-user","title":"Product-based Neural Networks for User Response Prediction","arxiv_id":"1611.00144","date":"2016-11-01","proceeding":null,"authors":["Yanru Qu","Han Cai","Kan Ren","Wei-Nan Zhang","Yong Yu","Ying Wen","Jun Wang"],"abstract":"Predicting user responses, such as clicks and conversions, is of great\nimportance and has found its usage in many Web applications including\nrecommender systems, web search and online advertising. The data in those\napplications is mostly categorical and contains multiple fields; a typical\nrepresentation is to transform it into a high-dimensional sparse binary feature\nrepresentation via one-hot encoding. Facing with the extreme sparsity,\ntraditional models may limit their capacity of mining shallow patterns from the\ndata, i.e. low-order feature combinations. Deep models like deep neural\nnetworks, on the other hand, cannot be directly applied for the\nhigh-dimensional input because of the huge feature space. In this paper, we\npropose a Product-based Neural Networks (PNN) with an embedding layer to learn\na distributed representation of the categorical data, a product layer to\ncapture interactive patterns between inter-field categories, and further fully\nconnected layers to explore high-order feature interactions. Our experimental\nresults on two large-scale real-world ad click datasets demonstrate that PNNs\nconsistently outperform the state-of-the-art models on various metrics.","url_abs":"http://arxiv.org/abs/1611.00144v1","url_pdf":"http://arxiv.org/pdf/1611.00144v1.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":"product-based-neural-networks-for-user","repo_url":"https://github.com/Atomu2014/product-nets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/Atomu2014/product-nets-distributed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/JianzhouZhan/Awesome-RecSystem-Models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/UlionTse/mlgb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/jamesdvance/predicting_clicks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/shenweichen/DeepCTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/shenweichen/DeepCTR-Torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/tangxyw/RecAlgorithm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/wangweitong/DL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/wangweitong/recommend_system","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"product-based-neural-networks-for-user","repo_url":"https://github.com/xue-pai/FuxiCTR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"click-through-rate-prediction","task_name":"Click-Through Rate Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/click-through-rate-prediction-on-amazon","task":"Click-Through Rate Prediction","dataset":"Amazon","model":"PNN","rank_in_archive_order":4,"of":5,"metrics":{"AUC":"0.8679"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-bing-news","task":"Click-Through Rate Prediction","dataset":"Bing News","model":"PNN","rank_in_archive_order":4,"of":7,"metrics":{"AUC":"0.8321","Log Loss":"0.2775"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-company","task":"Click-Through Rate Prediction","dataset":"Company*","model":"PNN*","rank_in_archive_order":4,"of":8,"metrics":{"AUC":"0.8672","Log Loss":"0.02636"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-company","task":"Click-Through Rate Prediction","dataset":"Company*","model":"IPNN","rank_in_archive_order":5,"of":8,"metrics":{"AUC":"0.8664","Log Loss":"0.02637"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-company","task":"Click-Through Rate Prediction","dataset":"Company*","model":"OPNN","rank_in_archive_order":7,"of":8,"metrics":{"AUC":"0.8658","Log Loss":"0.02641"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-criteo","task":"Click-Through Rate Prediction","dataset":"Criteo","model":"PNN*","rank_in_archive_order":35,"of":39,"metrics":{"AUC":"0.7987","Log Loss":"0.45214"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-criteo","task":"Click-Through Rate Prediction","dataset":"Criteo","model":"OPNN","rank_in_archive_order":36,"of":39,"metrics":{"AUC":"0.7982","Log Loss":"0.45256"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-criteo","task":"Click-Through Rate Prediction","dataset":"Criteo","model":"IPNN","rank_in_archive_order":38,"of":39,"metrics":{"AUC":"0.7972","Log Loss":"0.45323"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-dianping","task":"Click-Through Rate Prediction","dataset":"Dianping","model":"PNN","rank_in_archive_order":3,"of":5,"metrics":{"AUC":"0.8445","Log Loss":"0.3424"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-movielens","task":"Click-Through Rate Prediction","dataset":"MovieLens 20M","model":"PNN","rank_in_archive_order":5,"of":6,"metrics":{"AUC":"0.7321"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-ipinyou","task":"Click-Through Rate Prediction","dataset":"iPinYou","model":"OPNN","rank_in_archive_order":1,"of":7,"metrics":{"AUC":"0.8174"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-ipinyou","task":"Click-Through Rate Prediction","dataset":"iPinYou","model":"IPNN","rank_in_archive_order":2,"of":7,"metrics":{"AUC":"0.7914"},"uses_additional_data":false},{"leaderboard":"/sota/click-through-rate-prediction-on-ipinyou","task":"Click-Through Rate Prediction","dataset":"iPinYou","model":"PNN*","rank_in_archive_order":6,"of":7,"metrics":{"AUC":"0.7661"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.00144","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}