{"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-sequence-learning-with-auxiliary","title":"Deep Sequence Learning with Auxiliary Information for Traffic Prediction","arxiv_id":"1806.07380","date":"2018-06-13","proceeding":null,"authors":["Binbing Liao","Jingqing Zhang","Chao Wu","Douglas McIlwraith","Tong Chen","Shengwen Yang","Yike Guo","Fei Wu"],"abstract":"Predicting traffic conditions from online route queries is a challenging task\nas there are many complicated interactions over the roads and crowds involved.\nIn this paper, we intend to improve traffic prediction by appropriate\nintegration of three kinds of implicit but essential factors encoded in\nauxiliary information. We do this within an encoder-decoder sequence learning\nframework that integrates the following data: 1) offline geographical and\nsocial attributes. For example, the geographical structure of roads or public\nsocial events such as national celebrations; 2) road intersection information.\nIn general, traffic congestion occurs at major junctions; 3) online crowd\nqueries. For example, when many online queries issued for the same destination\ndue to a public performance, the traffic around the destination will\npotentially become heavier at this location after a while. Qualitative and\nquantitative experiments on a real-world dataset from Baidu have demonstrated\nthe effectiveness of our framework.","url_abs":"http://arxiv.org/abs/1806.07380v1","url_pdf":"http://arxiv.org/pdf/1806.07380v1.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-sequence-learning-with-auxiliary","repo_url":"https://github.com/JingqingZ/BaiduTraffic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"traffic-prediction","task_name":"Traffic Prediction"}],"methods":[],"datasets_introduced":[{"slug":"q-traffic","name":"Q-Traffic","full_name":null}],"methods_introduced":[],"results":[{"leaderboard":"/sota/traffic-prediction-on-q-traffic","task":"Traffic Prediction","dataset":"Q-Traffic","model":"hybrid Seq2Seq","rank_in_archive_order":1,"of":1,"metrics":{"MAPE":"8.63"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.07380","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}