Passenger Demand Prediction With Cellular Footprints

被引:7
作者
Chu, Jing [1 ]
Qian, Kun [1 ]
Wang, Xu [1 ]
Yao, Lina [2 ]
Xiao, Fu [3 ]
Li, Jianbo [4 ]
Miao, Xin
Yang, Zheng [1 ]
机构
[1] Tsinghua Univ, Sch Software Engn, Beijing 100084, Peoples R China
[2] UNSW, Sch Comp Sci & Engn, Kensington, NSW 2052, Australia
[3] Nanjing Univ Posts & Telecommun, Coll Comp, Nanjing 210003, Peoples R China
[4] Qingdao Univ, Comp Sci & Technol Coll, Qingdao 266071, Peoples R China
关键词
Urban areas; Meteorology; Computer architecture; Poles and towers; Microprocessors; Predictive models; Correlation; Machine learning; prediction methods; predictive models; mobile computing; communication systems; mobile communication; RIDE SERVICES; TIME;
D O I
10.1109/TMC.2020.3005240
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Accurate forecast of citywide passenger demand helps online car-hailing service providers to better schedule driver supplies. Previous research either uses only passenger order history and fails to capture the deep dependency of passenger demand, or is restricted on grid region partition that loses physical context. Recent advance in mobile traffic analysis has fostered understanding of city functions. In this article, we propose FlowFlexDP, a demand prediction model that integrates regional crowd flow and applies to flexible region partition. Analysis on a cellular dataset covering 1.5 million users in a major city in China reveals strong correlation between passenger demand and crowd flow. FlowFlexDP extracts both order history and crowd flow from cellular data, and adopts Graph Convolutional Neural Network to adapt prediction for regions of arbitrary shapes and sizes in a city. Evaluation on a large scale data set of 6 online car-hailing applications from cellular data shows that FlowFlexDP accurately predicts passenger demand and outperforms the state-of-the-art demand prediction methods.
引用
收藏
页码:252 / 263
页数:12
相关论文
共 54 条
[1]  
Abadi M., 2016, ARXIV160304467
[2]  
[Anonymous], 2012, P ACM SIGKDD INT WOR, DOI DOI 10.1145/2346496.2346498
[3]   Inferring Unmet Demand from Taxi Probe Data [J].
Anwar, Afian ;
Odoni, Amedeo ;
Rus, Daniela .
2015 IEEE 18TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015, :861-868
[4]   Urban Sensing Using Mobile Phone Network Data: A Survey of Research [J].
Calabrese, Francesco ;
Ferrari, Laura ;
Blondel, Vincent D. .
ACM COMPUTING SURVEYS, 2015, 47 (02)
[5]  
Chen QJ, 2016, AAAI CONF ARTIF INTE, P338
[6]   Understanding ridesplitting behavior of on-demand ride services: An ensemble learning approach [J].
Chen, Xiqun ;
Zahiri, Majid ;
Zhang, Shuaichao .
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2017, 76 :51-70
[7]  
Dark Sky, 2017, WEATH DAT
[8]  
Defferrard M, 2016, ADV NEUR IN, V29
[9]   Extracting urban functional regions from points of interest and human activities on location-based social networks [J].
Gao, Song ;
Janowicz, Krzysztof ;
Couclelis, Helen .
TRANSACTIONS IN GIS, 2017, 21 (03) :446-467
[10]   CLSTERS: A general system for reducing errors of trajectories under challenging localization situations [J].
Hao, W.U. ;
Weiwei, S.U.N. ;
Zheng, Baihua ;
Yang, Li ;
Zhou, Wei .
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2017, 1 (03)