TY - JOUR
T1 - Hexagon-Based Convolutional Neural Network for Supply-Demand Forecasting of Ride-Sourcing Services
AU - Ke, Jintao
AU - Yang, Hai
AU - Zheng, Hongyu
AU - Chen, Xiqun
AU - Jia, Yitian
AU - Gong, Pinghua
AU - Ye, Jieping
N1 - Funding Information:
Manuscript received December 26, 2017; revised August 22, 2018 and November 4, 2018; accepted November 14, 2018. Date of publication December 7, 2018; date of current version November 6, 2019. This work was supported in part by the Hong Kong’s Research Grants Council under Grant HKUST16222916, in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LR17E080002, in part by the National Natural Science Foundation of China under Grant 51508505, Grant 71771198, and Grant 51338008, in part by the Fundamental Research Funds for the Central Universities under Grant 2017QNA4025, and in part by the Key Research and Development Program of Zhejiang under Grant 2018C01007. The Associate Editor for this article was N. Geroliminis. (Corresponding author: Xiqun Chen.) J. Ke and H. Yang are with the Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong (e-mail: [email protected]; [email protected]).
Publisher Copyright:
© 2000-2011 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Ride-sourcing services are becoming an increasingly popular transportation mode in cities all over the world. With real-time information from both drivers and passengers, the ride-sourcing platform can reduce matching frictions and improve efficiencies by surge pricing, optimal vehicle-trip assignment, and proactive ridesplitting strategies. An important foundation of these strategies is the short-term supply-demand forecasting. In this paper, we tackle the problem of predicting the short-term supply-demand gap of ride-sourcing services. In contrast to the previous studies that partitioned a city area into numerous square lattices, we partition the city area into various regular hexagon lattices, which is motivated by the fact that hexagonal segmentation has an unambiguous neighborhood definition, smaller edge-to-area ratio, and isotropy. To capture the spatio-temporal characteristics in a hexagonal manner, we propose three hexagon-based convolutional neural networks (H-CNN), both the input and output of which are numerous local hexagon maps. Moreover, a hexagon-based ensemble mechanism is developed to enhance the prediction performance. Validated by a 3-week real-world ride-sourcing dataset in Guangzhou, China, the H-CNN models are found to significantly outperform the benchmark algorithms in terms of accuracy and robustness. Our approaches can be further extended to a broad range of spatio-temporal forecasting problems in the domain of shared mobility and urban computing.
AB - Ride-sourcing services are becoming an increasingly popular transportation mode in cities all over the world. With real-time information from both drivers and passengers, the ride-sourcing platform can reduce matching frictions and improve efficiencies by surge pricing, optimal vehicle-trip assignment, and proactive ridesplitting strategies. An important foundation of these strategies is the short-term supply-demand forecasting. In this paper, we tackle the problem of predicting the short-term supply-demand gap of ride-sourcing services. In contrast to the previous studies that partitioned a city area into numerous square lattices, we partition the city area into various regular hexagon lattices, which is motivated by the fact that hexagonal segmentation has an unambiguous neighborhood definition, smaller edge-to-area ratio, and isotropy. To capture the spatio-temporal characteristics in a hexagonal manner, we propose three hexagon-based convolutional neural networks (H-CNN), both the input and output of which are numerous local hexagon maps. Moreover, a hexagon-based ensemble mechanism is developed to enhance the prediction performance. Validated by a 3-week real-world ride-sourcing dataset in Guangzhou, China, the H-CNN models are found to significantly outperform the benchmark algorithms in terms of accuracy and robustness. Our approaches can be further extended to a broad range of spatio-temporal forecasting problems in the domain of shared mobility and urban computing.
KW - deep learning (DL)
KW - hexagon-based convolutional neural network (H-CNN)
KW - on-demand ride service
KW - ride-sourcing service
KW - Short-term supply-demand forecasting
UR - http://www.scopus.com/inward/record.url?scp=85058174929&partnerID=8YFLogxK
U2 - 10.1109/TITS.2018.2882861
DO - 10.1109/TITS.2018.2882861
M3 - Journal article
AN - SCOPUS:85058174929
SN - 1524-9050
VL - 20
SP - 4160
EP - 4173
JO - IEEE Transactions on Intelligent Transportation Systems
JF - IEEE Transactions on Intelligent Transportation Systems
IS - 11
M1 - 8566163
ER -