FGST: Fine-grained spatial-temporal based regression for stationless bike traffic prediction

Hao Chen; Senzhang Wang; Zengde Deng; Xiaoming Zhang; Zhoujun Li

doi:10.1007/978-3-030-16148-4_21

FGST: Fine-grained spatial-temporal based regression for stationless bike traffic prediction

Hao Chen
, Senzhang Wang
, Zengde Deng
, Xiaoming Zhang
, Zhoujun Li^*

^*Corresponding author for this work

Beihang University
Nanjing University of Aeronautics and Astronautics
Chinese University of Hong Kong

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

Currently, fully stationless bike sharing systems, such as Mobike and Ofo are becoming increasingly popular in both China and some big cities in the world. Different from traditional bike sharing systems that have to build a set of bike stations at different locations of a city and each station is associated with a fixed number of bike docks, there are no stations in stationless bike sharing systems. Thus users can flexibly check-out/return the bikes at arbitrary locations. Such a brand new bike-sharing mode better meets people’s short travel demand, but also poses new challenges for performing effective system management due to the extremely unbalanced bike usage demand in different areas and time intervals. Therefore, it is crucial to accurately predict the future bike traffic for helping the service provider rebalance the bikes timely. In this paper, we propose a Fine-Grained Spatial-Temporal based regression model named FGST to predict the future bike traffic in a stationless bike sharing system. We motivate the method via discovering the spatial-temporal correlation and the localized conservative rules of the bike check-out and check-in patterns. Our model also makes use of external factors like Point-Of-Interest(POI) informations to improve the prediction. Extensive experiments on a large Mobike trip dataset demonstrate that our approach outperforms baseline methods by a significant margin.

Original language	English
Title of host publication	Advances in Knowledge Discovery and Data Mining - 23rd Pacific-Asia Conference, PAKDD 2019, Proceedings
Editors	Qiang Yang, Zhi-Hua Zhou, Zhiguo Gong, Min-Ling Zhang, Sheng-Jun Huang
Publisher	Springer Verlag
Pages	265-279
Number of pages	15
ISBN (Print)	9783030161477
DOIs	https://doi.org/10.1007/978-3-030-16148-4_21
State	Published - 2019
Event	23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2019 - Macau, China Duration: 14 Apr 2019 → 17 Apr 2019

Publication series

Name	Lecture Notes in Computer Science
Volume	11439 LNAI
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2019
Country/Territory	China
City	Macau
Period	14/04/19 → 17/04/19

Keywords

Sharing-bikes
Spatial-temporal data
Traffic prediction

Access to Document

10.1007/978-3-030-16148-4_21

Cite this

Chen, H., Wang, S., Deng, Z., Zhang, X., & Li, Z. (2019). FGST: Fine-grained spatial-temporal based regression for stationless bike traffic prediction. In Q. Yang, Z.-H. Zhou, Z. Gong, M.-L. Zhang, & S.-J. Huang (Eds.), Advances in Knowledge Discovery and Data Mining - 23rd Pacific-Asia Conference, PAKDD 2019, Proceedings (pp. 265-279). (Lecture Notes in Computer Science; Vol. 11439 LNAI). Springer Verlag. https://doi.org/10.1007/978-3-030-16148-4_21

Chen, Hao ; Wang, Senzhang ; Deng, Zengde et al. / FGST : Fine-grained spatial-temporal based regression for stationless bike traffic prediction. Advances in Knowledge Discovery and Data Mining - 23rd Pacific-Asia Conference, PAKDD 2019, Proceedings. editor / Qiang Yang ; Zhi-Hua Zhou ; Zhiguo Gong ; Min-Ling Zhang ; Sheng-Jun Huang. Springer Verlag, 2019. pp. 265-279 (Lecture Notes in Computer Science).

@inproceedings{403f00dbe9bc44ecb423afbf63df2e0c,

title = "FGST: Fine-grained spatial-temporal based regression for stationless bike traffic prediction",

abstract = "Currently, fully stationless bike sharing systems, such as Mobike and Ofo are becoming increasingly popular in both China and some big cities in the world. Different from traditional bike sharing systems that have to build a set of bike stations at different locations of a city and each station is associated with a fixed number of bike docks, there are no stations in stationless bike sharing systems. Thus users can flexibly check-out/return the bikes at arbitrary locations. Such a brand new bike-sharing mode better meets people{\textquoteright}s short travel demand, but also poses new challenges for performing effective system management due to the extremely unbalanced bike usage demand in different areas and time intervals. Therefore, it is crucial to accurately predict the future bike traffic for helping the service provider rebalance the bikes timely. In this paper, we propose a Fine-Grained Spatial-Temporal based regression model named FGST to predict the future bike traffic in a stationless bike sharing system. We motivate the method via discovering the spatial-temporal correlation and the localized conservative rules of the bike check-out and check-in patterns. Our model also makes use of external factors like Point-Of-Interest(POI) informations to improve the prediction. Extensive experiments on a large Mobike trip dataset demonstrate that our approach outperforms baseline methods by a significant margin.",

keywords = "Sharing-bikes, Spatial-temporal data, Traffic prediction",

author = "Hao Chen and Senzhang Wang and Zengde Deng and Xiaoming Zhang and Zhoujun Li",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2019.; 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2019 ; Conference date: 14-04-2019 Through 17-04-2019",

year = "2019",

doi = "10.1007/978-3-030-16148-4\_21",

language = "英语",

isbn = "9783030161477",

series = "Lecture Notes in Computer Science",

publisher = "Springer Verlag",

pages = "265--279",

editor = "Qiang Yang and Zhi-Hua Zhou and Zhiguo Gong and Min-Ling Zhang and Sheng-Jun Huang",

booktitle = "Advances in Knowledge Discovery and Data Mining - 23rd Pacific-Asia Conference, PAKDD 2019, Proceedings",

address = "德国",

}

Chen, H, Wang, S, Deng, Z, Zhang, X & Li, Z 2019, FGST: Fine-grained spatial-temporal based regression for stationless bike traffic prediction. in Q Yang, Z-H Zhou, Z Gong, M-L Zhang & S-J Huang (eds), Advances in Knowledge Discovery and Data Mining - 23rd Pacific-Asia Conference, PAKDD 2019, Proceedings. Lecture Notes in Computer Science, vol. 11439 LNAI, Springer Verlag, pp. 265-279, 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2019, Macau, China, 14/04/19. https://doi.org/10.1007/978-3-030-16148-4_21

FGST: Fine-grained spatial-temporal based regression for stationless bike traffic prediction. / Chen, Hao; Wang, Senzhang; Deng, Zengde et al.
Advances in Knowledge Discovery and Data Mining - 23rd Pacific-Asia Conference, PAKDD 2019, Proceedings. ed. / Qiang Yang; Zhi-Hua Zhou; Zhiguo Gong; Min-Ling Zhang; Sheng-Jun Huang. Springer Verlag, 2019. p. 265-279 (Lecture Notes in Computer Science; Vol. 11439 LNAI).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - FGST

T2 - 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2019

AU - Chen, Hao

AU - Wang, Senzhang

AU - Deng, Zengde

AU - Zhang, Xiaoming

AU - Li, Zhoujun

N1 - Publisher Copyright: © Springer Nature Switzerland AG 2019.

PY - 2019

Y1 - 2019

N2 - Currently, fully stationless bike sharing systems, such as Mobike and Ofo are becoming increasingly popular in both China and some big cities in the world. Different from traditional bike sharing systems that have to build a set of bike stations at different locations of a city and each station is associated with a fixed number of bike docks, there are no stations in stationless bike sharing systems. Thus users can flexibly check-out/return the bikes at arbitrary locations. Such a brand new bike-sharing mode better meets people’s short travel demand, but also poses new challenges for performing effective system management due to the extremely unbalanced bike usage demand in different areas and time intervals. Therefore, it is crucial to accurately predict the future bike traffic for helping the service provider rebalance the bikes timely. In this paper, we propose a Fine-Grained Spatial-Temporal based regression model named FGST to predict the future bike traffic in a stationless bike sharing system. We motivate the method via discovering the spatial-temporal correlation and the localized conservative rules of the bike check-out and check-in patterns. Our model also makes use of external factors like Point-Of-Interest(POI) informations to improve the prediction. Extensive experiments on a large Mobike trip dataset demonstrate that our approach outperforms baseline methods by a significant margin.

AB - Currently, fully stationless bike sharing systems, such as Mobike and Ofo are becoming increasingly popular in both China and some big cities in the world. Different from traditional bike sharing systems that have to build a set of bike stations at different locations of a city and each station is associated with a fixed number of bike docks, there are no stations in stationless bike sharing systems. Thus users can flexibly check-out/return the bikes at arbitrary locations. Such a brand new bike-sharing mode better meets people’s short travel demand, but also poses new challenges for performing effective system management due to the extremely unbalanced bike usage demand in different areas and time intervals. Therefore, it is crucial to accurately predict the future bike traffic for helping the service provider rebalance the bikes timely. In this paper, we propose a Fine-Grained Spatial-Temporal based regression model named FGST to predict the future bike traffic in a stationless bike sharing system. We motivate the method via discovering the spatial-temporal correlation and the localized conservative rules of the bike check-out and check-in patterns. Our model also makes use of external factors like Point-Of-Interest(POI) informations to improve the prediction. Extensive experiments on a large Mobike trip dataset demonstrate that our approach outperforms baseline methods by a significant margin.

KW - Sharing-bikes

KW - Spatial-temporal data

KW - Traffic prediction

UR - https://www.scopus.com/pages/publications/85064894441

U2 - 10.1007/978-3-030-16148-4_21

DO - 10.1007/978-3-030-16148-4_21

M3 - 会议稿件

AN - SCOPUS:85064894441

SN - 9783030161477

T3 - Lecture Notes in Computer Science

SP - 265

EP - 279

BT - Advances in Knowledge Discovery and Data Mining - 23rd Pacific-Asia Conference, PAKDD 2019, Proceedings

A2 - Yang, Qiang

A2 - Zhou, Zhi-Hua

A2 - Gong, Zhiguo

A2 - Zhang, Min-Ling

A2 - Huang, Sheng-Jun

PB - Springer Verlag

Y2 - 14 April 2019 through 17 April 2019

ER -

Chen H, Wang S, Deng Z, Zhang X , Li Z. FGST: Fine-grained spatial-temporal based regression for stationless bike traffic prediction. In Yang Q, Zhou ZH, Gong Z, Zhang ML, Huang SJ, editors, Advances in Knowledge Discovery and Data Mining - 23rd Pacific-Asia Conference, PAKDD 2019, Proceedings. Springer Verlag. 2019. p. 265-279. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-16148-4_21

FGST: Fine-grained spatial-temporal based regression for stationless bike traffic prediction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this