@neal_lathia
dept. of computer science
university college london
ubicomp 2011
@neal_lathia
dept. of computer science
university college london
ubicomp 2011
the oyster card
a sensor carried by Londoners
the oyster card
beyond payment?
a sensor for science?
how smart is your smart card?
measuring travel behaviours, perceptions, and incentives
data vs. behaviour & perception
perception:
+ 25 question survey
data:
+ respondent oyster history

reference data:
+ 5%, 2 x 83-day sample
+ 100%, 1-month sample
trips taken


        data




               perception
travel time


         proportion




                      time bin
perceived/data payment
                         payment




user
perceived/data payment
                         payment




user
payment vs. reference




            compared to 3,379,570 transactions
            (5% data set):

            49.8% of transactions should fall into
            this category.
data vs. behaviour & perception
+ estimating travel time > estimating travel needs
+ users inaccurately estimate payments
+ high usage of modalities that are “never used”
+ high proportion of travel to “non typical” stations
the oyster card
beyond payment?
a sensor for science?
future ubicomp applications?
data vs. travel incentives
mobility vs. student discounts



184,923 students
10,723,472 student trips
48,888,268 non-student trips
mobility vs. student discounts
mobility vs. student discounts



“... as a student with a flexible
timetable, it isn't always obvious
whether a travel card is a better deal
than pay as you go...”
mobility vs. daily capping



91,391,155 pay as you go trips
split into capped vs. non-capped
           (free)     (non-free)
mobility vs. daily capping




not-free: 54.83% trips by bus
free: 73.53% trips by bus
the oyster card
a tool to evaluate policy?
a sensor to test incentives?
N. Lathia, J. Froehlich, L. Capra. Mining Public Transport
Usage for Personalised Intelligent Transport Systems. In
IEEE ICDM 2010, Sydney, Australia, December 2010.

N. Lathia, L. Capra. Mining Mobility Data to Minimise
Travellers' Spending on Public Transport. In ACM KDD 2011,
San Diego, USA, August 2011.
how smart is your smart card?
measuring travel behaviours, perceptions, and incentives



  @neal_lathia
  dept. of computer science
  university college london
  ubicomp 2011

How Smart is Your Smart Card?

  • 1.
    @neal_lathia dept. of computerscience university college london ubicomp 2011
  • 2.
    @neal_lathia dept. of computerscience university college london ubicomp 2011
  • 6.
    the oyster card asensor carried by Londoners
  • 7.
    the oyster card beyondpayment? a sensor for science?
  • 8.
    how smart isyour smart card? measuring travel behaviours, perceptions, and incentives
  • 9.
    data vs. behaviour& perception
  • 10.
    perception: + 25 questionsurvey data: + respondent oyster history reference data: + 5%, 2 x 83-day sample + 100%, 1-month sample
  • 11.
    trips taken data perception
  • 12.
    travel time proportion time bin
  • 13.
  • 14.
  • 15.
    payment vs. reference compared to 3,379,570 transactions (5% data set): 49.8% of transactions should fall into this category.
  • 16.
    data vs. behaviour& perception + estimating travel time > estimating travel needs + users inaccurately estimate payments + high usage of modalities that are “never used” + high proportion of travel to “non typical” stations
  • 17.
    the oyster card beyondpayment? a sensor for science? future ubicomp applications?
  • 18.
    data vs. travelincentives
  • 19.
    mobility vs. studentdiscounts 184,923 students 10,723,472 student trips 48,888,268 non-student trips
  • 20.
  • 21.
    mobility vs. studentdiscounts “... as a student with a flexible timetable, it isn't always obvious whether a travel card is a better deal than pay as you go...”
  • 22.
    mobility vs. dailycapping 91,391,155 pay as you go trips split into capped vs. non-capped (free) (non-free)
  • 23.
    mobility vs. dailycapping not-free: 54.83% trips by bus free: 73.53% trips by bus
  • 24.
    the oyster card atool to evaluate policy? a sensor to test incentives?
  • 26.
    N. Lathia, J.Froehlich, L. Capra. Mining Public Transport Usage for Personalised Intelligent Transport Systems. In IEEE ICDM 2010, Sydney, Australia, December 2010. N. Lathia, L. Capra. Mining Mobility Data to Minimise Travellers' Spending on Public Transport. In ACM KDD 2011, San Diego, USA, August 2011.
  • 27.
    how smart isyour smart card? measuring travel behaviours, perceptions, and incentives @neal_lathia dept. of computer science university college london ubicomp 2011