File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.trpro.2015.06.014
- Scopus: eid_2-s2.0-84959364396
- WOS: WOS:000380491000014
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: A two-stage approach to modeling vacant taxi movements
Title | A two-stage approach to modeling vacant taxi movements |
---|---|
Authors | |
Keywords | Two-stage approach Taxi customer-search Enhanced sequential logit model Logit-opportunity model Global positioning system data |
Issue Date | 2015 |
Publisher | Elsevier BV. The Journal's web site is located at tp://www.journals.elsevier.com/transportation-research-procedia/ |
Citation | The 21st International Symposium on Transportation and Traffic Theory (ISTTT 2015), Kobe, Japan, 5-7 August 2015. In Transportation Research Procedia, 2015, v. 7, p. 254-275 How to Cite? |
Abstract | In this paper, a two-stage modeling approach is proposed to predict vacant taxi movements in searching for customers. The taxi movement problem is formulated into a two-stage model that consists of two sub-models, namely the first and second stage sub-models. The first stage sub-model estimates the zone choice of vacant taxi drivers for customer-search and the second stage sub-model determines the circulation time and distance of vacant taxi drivers in each zone by capturing their local customer-search decisions in a cell-based network within the zone chosen in the first stage sub-model. These two sub-models are designed to influence each other, and hence an iterative solution procedure is introduced to solve for a convergent solution. The modeling concept, advantages, and applications are illustrated by the global positioning system data of 460 Hong Kong urban taxis. The results demonstrate that the proposed model formulation offers a great improvement in terms of root mean square error as compared with the existing taxi customer-search models, and show the model capabilities of predicting the changes in vacant taxi trip distributions with respect to the variations in the fleet size and fare. Potential taxi policies are investigated and discussed according to the findings to provide insights in managing the Hong Kong taxi market. Copyright © 2015 Elsevier B.V. |
Description | Open Access Original Research Article - Oral presentation: WY Szeto |
Persistent Identifier | http://hdl.handle.net/10722/215488 |
ISSN | 2023 SCImago Journal Rankings: 0.384 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wong, RCP | - |
dc.contributor.author | Szeto, WY | - |
dc.contributor.author | Wong, SC | - |
dc.date.accessioned | 2015-08-21T13:27:36Z | - |
dc.date.available | 2015-08-21T13:27:36Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | The 21st International Symposium on Transportation and Traffic Theory (ISTTT 2015), Kobe, Japan, 5-7 August 2015. In Transportation Research Procedia, 2015, v. 7, p. 254-275 | - |
dc.identifier.issn | 2352-1465 | - |
dc.identifier.uri | http://hdl.handle.net/10722/215488 | - |
dc.description | Open Access Original Research Article - Oral presentation: WY Szeto | - |
dc.description.abstract | In this paper, a two-stage modeling approach is proposed to predict vacant taxi movements in searching for customers. The taxi movement problem is formulated into a two-stage model that consists of two sub-models, namely the first and second stage sub-models. The first stage sub-model estimates the zone choice of vacant taxi drivers for customer-search and the second stage sub-model determines the circulation time and distance of vacant taxi drivers in each zone by capturing their local customer-search decisions in a cell-based network within the zone chosen in the first stage sub-model. These two sub-models are designed to influence each other, and hence an iterative solution procedure is introduced to solve for a convergent solution. The modeling concept, advantages, and applications are illustrated by the global positioning system data of 460 Hong Kong urban taxis. The results demonstrate that the proposed model formulation offers a great improvement in terms of root mean square error as compared with the existing taxi customer-search models, and show the model capabilities of predicting the changes in vacant taxi trip distributions with respect to the variations in the fleet size and fare. Potential taxi policies are investigated and discussed according to the findings to provide insights in managing the Hong Kong taxi market. Copyright © 2015 Elsevier B.V. | - |
dc.language | eng | - |
dc.publisher | Elsevier BV. The Journal's web site is located at tp://www.journals.elsevier.com/transportation-research-procedia/ | - |
dc.relation.ispartof | Transportation Research Procedia | - |
dc.subject | Two-stage approach | - |
dc.subject | Taxi customer-search | - |
dc.subject | Enhanced sequential logit model | - |
dc.subject | Logit-opportunity model | - |
dc.subject | Global positioning system data | - |
dc.title | A two-stage approach to modeling vacant taxi movements | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Wong, RCP: ryancpw@hku.hk | - |
dc.identifier.email | Szeto, WY: ceszeto@hku.hk | - |
dc.identifier.email | Wong, SC: hhecwsc@hku.hk | - |
dc.identifier.authority | Szeto, WY=rp01377 | - |
dc.identifier.authority | Wong, SC=rp00191 | - |
dc.description.nature | link_to_OA_fulltext | - |
dc.identifier.doi | 10.1016/j.trpro.2015.06.014 | - |
dc.identifier.scopus | eid_2-s2.0-84959364396 | - |
dc.identifier.hkuros | 250121 | - |
dc.identifier.hkuros | 250585 | - |
dc.identifier.hkuros | 250227 | - |
dc.identifier.volume | 7 | - |
dc.identifier.spage | 254 | - |
dc.identifier.epage | 275 | - |
dc.identifier.isi | WOS:000380491000014 | - |
dc.publisher.place | The Netherlands | - |
dc.customcontrol.immutable | sml 151008 | - |
dc.identifier.issnl | 2352-1457 | - |