Dynamic Flow Distribution Prediction for Urban Dockless E-Scooter Sharing Reconfiguration

Thanks to recent progresses in mobile payment, IoT, electric motors, batteries and location-based services, Dockless E-scooter Sharing (DES) has become a popular means of last-mile commute for a growing number of (smart) cities. As e-scooters are getting deployed dynamically and flexibly across city regions that expand and/or shrink, with subsequent social, commercial and environmental evaluation, accurate prediction of the distribution of e-scooters given reconfigured regions becomes essential for the city planners and service providers. To meet this need, we propose GCScoot, a novel dynamic flow distribution prediction for reconfiguring urban DES systems. Based on the real-world datasets with reconfiguration, we analyze the mobility features of the e-scooter distribution and flow dynamics for the data-driven designs. To adapt to dynamic reconfiguration of DES deployment, we propose a novel spatio-temporal graph capsule neural network within GCScoot to predict the future dockless e-scooter flows given the reconfigured regions. GCScoot preprocesses the historical spatial e-scooter distributions into flow graph structures, where discretized city regions are considered as nodes and their mutual flows as edges. Given data-driven designs regarding distance, ride flows and region connectivity, the dynamic region-to-region correlations embedded within the temporal flow graphs are captured through the graph capsule neural network which accurately predicts the DES flows. We have conducted extensive empirical studies upon three different e-scooter datasets (>2.8 million rides in total) in populous US cities including Austin TX, Louisville KY and Minneapolis MN. The evaluation results have corroborated the accuracy and effectiveness of GCScoot in predicting dynamic distribution of dockless e-scooters’ mobility.

[1]  Sang Hyuk Son,et al.  Towards Efficient Sharing: A Usage Balancing Mechanism for Bike Sharing Systems , 2019, WWW.

[2]  David S. Rosenblum,et al.  UrbanFM: Inferring Fine-Grained Urban Flows , 2019, KDD.

[3]  Xianfeng Tang,et al.  Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction , 2019, WWW.

[4]  Kang G. Shin,et al.  Spatio-Temporal Capsule-based Reinforcement Learning for Mobility-on-Demand Network Coordination , 2019, WWW.

[5]  Xin Yao,et al.  Predicting bike sharing demand using recurrent neural networks , 2018, IIKI.

[6]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[7]  Jieping Ye,et al.  Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting , 2019, AAAI.

[8]  Longbo Huang,et al.  Rebalancing Dockless Bike Sharing Systems , 2018, ArXiv.

[9]  Yi Luo,et al.  Dynamic Demand Prediction for Expanding Electric Vehicle Sharing Systems: A Graph Sequence Learning Approach , 2019, ArXiv.

[10]  Zhi-Li Zhang,et al.  Graph Capsule Convolutional Neural Networks , 2018, ArXiv.

[11]  Kang G. Shin,et al.  Spatio-temporal Adaptive Pricing for Balancing Mobility-on-Demand Networks , 2019, ACM Trans. Intell. Syst. Technol..

[12]  Yong Wang,et al.  Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction , 2017, Sensors.

[13]  Kang G. Shin,et al.  (Re)Configuring Bike Station Network via Crowdsourced Information Fusion and Joint Optimization , 2018, MobiHoc.

[14]  Yanmin Zhu,et al.  Where Will Dockless Shared Bikes be Stacked?: --- Parking Hotspots Detection in a New City , 2018, KDD.

[15]  Qiang Yang,et al.  Bike flow prediction with multi-graph convolutional networks , 2018, SIGSPATIAL/GIS.

[16]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[17]  Jiming Chen,et al.  Data-Driven Utilization-Aware Trip Advisor for Bike-Sharing Systems , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[18]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[19]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[20]  Chao Tian,et al.  Detecting Vehicle Illegal Parking Events using Sharing Bikes' Trajectories , 2018, KDD.

[21]  Jie Wu,et al.  Optimizing Rebalance Scheme for Dock-Less Bike Sharing Systems with Adaptive User Incentive , 2019, 2019 20th IEEE International Conference on Mobile Data Management (MDM).

[22]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[23]  Yanmin Zhu,et al.  Inferring Dockless Shared Bike Distribution in New Cities , 2018, WSDM.

[24]  Jiming Chen,et al.  Mobility Modeling and Prediction in Bike-Sharing Systems , 2016, MobiSys.

[25]  Joseph P Schwieterman,et al.  E-Scooter Scenarios: Evaluating the Potential Mobility Benefits of Shared Dockless Scooters in Chicago , 2018 .

[26]  Jun Wang,et al.  Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning , 2019, WWW.

[27]  Feng Liu,et al.  Cross-City Transfer Learning for Deep Spatio-Temporal Prediction , 2018, IJCAI.

[28]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[29]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[30]  Junbo Zhang,et al.  Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning , 2019, KDD.

[31]  Adam Wierman,et al.  Prices and Subsidies in the Sharing Economy , 2016, WWW.

[32]  Philip S. Yu,et al.  Bicycle-sharing systems expansion: station re-deployment through crowd planning , 2016, SIGSPATIAL/GIS.

[33]  Lihui Chen,et al.  Capsule Graph Neural Network , 2018, ICLR.

[34]  Markus Leitner,et al.  Determining optimal locations for charging stations of electric car-sharing systems under stochastic demand , 2017 .