File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Joint predictions of multi-modal ride-hailing demands: A deep multi-task multi-graph learning-based approach

TitleJoint predictions of multi-modal ride-hailing demands: A deep multi-task multi-graph learning-based approach
Authors
KeywordsDeep multi-task learning
Demand prediction
Multi-graph convolutional network
Ride-hailing
Issue Date2021
Citation
Transportation Research Part C: Emerging Technologies, 2021, v. 127, article no. 103063 How to Cite?
AbstractRide-hailing platforms generally provide various service options to customers, such as solo ride services, shared ride services, etc. It is generally expected that demands for different service modes are correlated, and the prediction of demand for one service mode can benefit from historical observations of demands for other service modes. Moreover, an accurate joint prediction of demands for multiple service modes can help the platforms better allocate and dispatch vehicle resources. Although there is a large stream of literature on ride-hailing demand predictions for one specific service mode, few efforts have been paid towards joint predictions of ride-hailing demands for multiple service modes. To address this issue, we propose a deep multi-task multi-graph learning approach, which combines two components: (1) multiple multi-graph convolutional (MGC) networks for predicting demands for different service modes, and (2) multi-task learning modules that enable knowledge sharing across multiple MGC networks. More specifically, two multi-task learning structures are established. The first one is the regularized cross-task learning, which builds cross-task connections among the inputs and outputs of multiple MGC networks. The second one is the multi-linear relationship learning, which imposes a prior tensor normal distribution on the weights of various MGC networks. Although there are no concrete bridges between different MGC networks, the weights of these networks are constrained by each other and subject to a common prior distribution. Evaluated with the for-hire-vehicle datasets in Manhattan, we show that our proposed approach outperforms the benchmark algorithms in prediction accuracy for different ride-hailing modes.
Persistent Identifierhttp://hdl.handle.net/10722/308925
ISSN
2023 Impact Factor: 7.6
2023 SCImago Journal Rankings: 2.860
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorKe, Jintao-
dc.contributor.authorFeng, Siyuan-
dc.contributor.authorZhu, Zheng-
dc.contributor.authorYang, Hai-
dc.contributor.authorYe, Jieping-
dc.date.accessioned2021-12-08T07:50:25Z-
dc.date.available2021-12-08T07:50:25Z-
dc.date.issued2021-
dc.identifier.citationTransportation Research Part C: Emerging Technologies, 2021, v. 127, article no. 103063-
dc.identifier.issn0968-090X-
dc.identifier.urihttp://hdl.handle.net/10722/308925-
dc.description.abstractRide-hailing platforms generally provide various service options to customers, such as solo ride services, shared ride services, etc. It is generally expected that demands for different service modes are correlated, and the prediction of demand for one service mode can benefit from historical observations of demands for other service modes. Moreover, an accurate joint prediction of demands for multiple service modes can help the platforms better allocate and dispatch vehicle resources. Although there is a large stream of literature on ride-hailing demand predictions for one specific service mode, few efforts have been paid towards joint predictions of ride-hailing demands for multiple service modes. To address this issue, we propose a deep multi-task multi-graph learning approach, which combines two components: (1) multiple multi-graph convolutional (MGC) networks for predicting demands for different service modes, and (2) multi-task learning modules that enable knowledge sharing across multiple MGC networks. More specifically, two multi-task learning structures are established. The first one is the regularized cross-task learning, which builds cross-task connections among the inputs and outputs of multiple MGC networks. The second one is the multi-linear relationship learning, which imposes a prior tensor normal distribution on the weights of various MGC networks. Although there are no concrete bridges between different MGC networks, the weights of these networks are constrained by each other and subject to a common prior distribution. Evaluated with the for-hire-vehicle datasets in Manhattan, we show that our proposed approach outperforms the benchmark algorithms in prediction accuracy for different ride-hailing modes.-
dc.languageeng-
dc.relation.ispartofTransportation Research Part C: Emerging Technologies-
dc.subjectDeep multi-task learning-
dc.subjectDemand prediction-
dc.subjectMulti-graph convolutional network-
dc.subjectRide-hailing-
dc.titleJoint predictions of multi-modal ride-hailing demands: A deep multi-task multi-graph learning-based approach-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.trc.2021.103063-
dc.identifier.scopuseid_2-s2.0-85103776909-
dc.identifier.volume127-
dc.identifier.spagearticle no. 103063-
dc.identifier.epagearticle no. 103063-
dc.identifier.isiWOS:000656963900007-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats