{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:38:45Z","timestamp":1761176325664,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Traffic forecasting is an attractive research direction of fundamental importance that underpins next-generation traffic management. While recent progress has been driven by deep learning techniques, existing approaches often rely on historical observation to make predictions and exhibit fragility in handling rare but critical scenarios such as holiday congestion, thereby limiting their practical applicability in real-world traffic management processes. To fill this gap, we propose a novel framework as an actionable solution for practical traffic management scenarios. Our method is based on two key insights: a) route search data encodes rich travel intentions in holiday and b) traffic forecasting should be formulated as a conditional generation task to deal with the inherent challenge from bias dataset. We develop a diffusion-based model and train it on large-scale datasets containing 450 million route search records and three years of traffic data. Our method demonstrates remarkable capacity to forecast challenging holiday traffic states (speed, traffic volume and congestion), with superior performance compared to state-of-the-art deep learning baselines and experts.<\/jats:p>","DOI":"10.3233\/faia251481","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:04:10Z","timestamp":1761127450000},"source":"Crossref","is-referenced-by-count":0,"title":["Diffusion Model Bridges Search Behavior and Travel Needs for Practical Traffic Forecasting"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8838-7306","authenticated-orcid":false,"given":"Lifeng","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Interdisciplinary Information Studies, the University of Tokyo, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8025-3013","authenticated-orcid":false,"given":"Hangli","family":"Ge","sequence":"additional","affiliation":[{"name":"Interfaculty Initiative in Information Studies, the University of Tokyo, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4728-9425","authenticated-orcid":false,"given":"Noboru","family":"Koshizuka","sequence":"additional","affiliation":[{"name":"Interfaculty Initiative in Information Studies, the University of Tokyo, Tokyo, Japan"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:04:11Z","timestamp":1761127451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251481"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251481","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}