making sense of big data from ride-sharing...

20
Making Sense of Big Data from Ride-Sharing Services Yanhua Li Assistant Professor Computer Science Department Worcester Polytechnic Institute

Upload: others

Post on 17-Jun-2020

1 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Making Sense of Big Data from Ride-Sharing Services

Yanhua LiAssistant Professor

Computer Science DepartmentWorcester Polytechnic Institute

Page 2: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Who am I?

Yanhua Li, PhDAssistant ProfessorComputer Science & Data ScienceWorcester Polytechnic Institute (WPI)

PhD, Computer Science, U of Minnesota, 2013PhD, Electrical Engineering, BUPT, 2009

Research Interests: Big data analytics, Smart Cities, Measurement, Spatio-temporal Data Mining

Industrial Experience: HUAWEI Noah’s Ark Lab, Mobike, DiDi

Page 3: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services

Guanxiong Liu, Yanhua Li, Zhi-Li Zhang, Jun Luo, Fan Zhang

WPI, CAS, Lenovo, UMNContact: [email protected]

ACM SIGSPATIAL 2017

Page 4: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Today’s Urban Transit ServicesPrivate TransitPublic Transits

affordable ride-sharing services reduce the personal vehicle usage

Page 5: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Limitations of Today’s Public Transits• Fixed Routes and Time Tables

– Transit supply mis-match dynamic demands

• Large number of stops and transfers– Long travel time

Page 6: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Limitations of Today’s Private Transits• Expensive

– High operation cost, – Due to the exclusive service

• Service delay– On-demand services– Delay after the service request

• Transit modes run independently– Lack of inter-transit coordination

Page 7: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Future Smart TransitToday’s Transits• Private Transits

– High Cost– Service delay

• Public Transits– Fixed routes– Fixed timetable– Long travel time

• No Inter-Transit Coordination

• Dynamic services– Real time trip

demands• Short travel time

– as private transits• Low cost

– as public transits

Future Urban Transit Services

Private Transits: Point-to-point modePublic Transits: fixed route mode

Page 8: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Hub-and-Spoke Transit Mode

Airlines routes

• Traffic move along spokes connected via a few hubs– Less operation cost (than private), thus lower cost– Less stops/stations (than public), thus lower transit time

• A promising transit mode, and how to design it in urban areas?

Package delivery system

Page 9: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

CityLines Transit System• CityLines: a Hybrid Hub-and-Spoke Transit Mode

– point-to-point mode: high demand source-destination pairs– hub-and-spoke mode: low demand source-destination pairs

D1

S1

D1S2

S3

D2

D3D4

S1

D1S2

S3

D2

D3D4

Private transitPoint-to-point model

CityLinesHybrid hub-and-spoke mode

Reduce routes, thus operation cost

S1

D1S2

S3

D2

D3

D4

Reduce stops/stations, thus travel time

Public transitFixed-route model

Page 10: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Input Data Description• Trip Demand Data (in Shenzhen):

• Source: Taxi GPS, Bus, Subway Transactions• Duration: March 1st–30th, 2014. • Size: 19,428,453 trips in all transit modes• Format: Taxi ID, time, latitude, longitude, load

• Road Map, Subway Lines, and Bus routes:

Page 11: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

https://wpi.edu/~yli15/CityLines/

CityLines Demo System

Page 12: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Planning Bike Lanes Based on Sharing-Bikes’ Trajectories

StartSegments

StartSegments

StartSegments

Jie Bao, Tianfu He, Sijie Ruan, Yanhua Li, Yu Zheng

Microsoft ResearchWorcester Polytechnic Institute

ACM KDD 2017

Page 13: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Bike “Renaissance” in China1980s 2017

Owning a bike Sharing a bike

Page 14: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Effective Bike Lanes PromoteCycling Experiences

• Motivations to promote cycling– Reduce the air pollution– Ease traffic congestions

– Address the “last mile” in public transportation

– Advocate the healthier lifestyle

Page 15: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Why Sharing Bike (Mobike) Trajectories

• Large Number of Users– Better coverage of general

bike users*1 Billion Users, 25 Million Daily Orders

• Station-Less Deployment– More realistic travel

demands• Detailed Trajectory Data

– More information on mobility patterns

QRcodetolock/unlock

GPS/3GModule

*http://www.hbspcar.com/1922.html

Page 16: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Mobike Data Description• Dates from 2016/09/01 to 2016/09/30.• 13,063 users, 3,971 bikes, and 230,303 trajectories.

Significant Usage Drop at 30 min

Page 17: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Problem Settings

• Government Requirements– Budget Constraints– Best Serve the Public (coverage & continuity)– Construction/Management Convenience

ShanghaiHongqiaoAirport

Road Space & Money

s1=2km

User & Trip Coverage K-Connected Components

Page 18: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

JinyunRoadStation

WandaPlaza

Existing Bike Lanes

Highly Populated Residential Area

Page 19: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

• Dockless bike-sharing– Load balancing strategies– Incentive mechanisms

• Ride-hailing– Driver behavior analysis– Smart traffic management

On-going projects

Page 20: Making Sense of Big Data from Ride-Sharing Servicessharingeconomy.umn.edu/events/workshop/2017/documents/7...CityLines: A Hybrid Hub-and-Spoke System for Urban Transit Services Guanxiong

Questions?