No More Cruisin' for Parking: Targeted Information and Incentives via Spatio-Temporal Analysis and Bandits
Tanner Fiez

Citation
Tanner Fiez. "No More Cruisin' for Parking: Targeted Information and Incentives via Spatio-Temporal Analysis and Bandits". Talk or presentation, 24, August, 2017.

Abstract
Many considerations factor into parking policy, including balancing competing needs (transit, customers, residents, shared vehicles, etc.), moving goods and people efficiently, and supporting business district vitality. Policies, however, can have unintended consequences such as added congestion. To mitigate congestion while meeting a city's diverse needs, a variety of techniques including performance based pricing, targeted ad campaigns, and incentives have been proposed. In practice, cities have yet to exploit the full potential of rich data streams now available in designing such mechanisms. In this talk, we discuss our recent work on leveraging Gaussian mixture models applied to transaction data to identify locations with similar demand characteristics and ongoing work on a multi-armed bandit approach to match incentives and ad campaigns to locations and user groups within them. To capture the impact of matches we model user preferences as time-varying stochastic processes that depend on the offered mechanism. We are collaborating with the Seattle Department of Transportation to test the proposed techniques in a living lab scenario in which we target information to potential parkers and gather feedback via environmental sensors and user surveys to assess outcomes.

Electronic downloads


Internal. This publication has been marked by the author for FORCES-only distribution, so electronic downloads are not available without logging in.
Citation formats  
  • HTML
    Tanner Fiez. <a
    href="http://www.cps-forces.org/pubs/281.html"
    ><i>No More Cruisin' for Parking: Targeted
    Information and Incentives via Spatio-Temporal Analysis and
    Bandits</i></a>, Talk or presentation,  24,
    August, 2017.
  • Plain text
    Tanner Fiez. "No More Cruisin' for Parking: Targeted
    Information and Incentives via Spatio-Temporal Analysis and
    Bandits". Talk or presentation,  24, August, 2017.
  • BibTeX
    @presentation{Fiez17_NoMoreCruisinForParkingTargetedInformationIncentives,
        author = {Tanner Fiez},
        title = {No More Cruisin' for Parking: Targeted Information
                  and Incentives via Spatio-Temporal Analysis and
                  Bandits},
        day = {24},
        month = {August},
        year = {2017},
        abstract = {Many considerations factor into parking policy,
                  including balancing competing needs (transit,
                  customers, residents, shared vehicles, etc.),
                  moving goods and people efficiently, and
                  supporting business district vitality. Policies,
                  however, can have unintended consequences such as
                  added congestion. To mitigate congestion while
                  meeting a city's diverse needs, a variety of
                  techniques including performance based pricing,
                  targeted ad campaigns, and incentives have been
                  proposed. In practice, cities have yet to exploit
                  the full potential of rich data streams now
                  available in designing such mechanisms. In this
                  talk, we discuss our recent work on leveraging
                  Gaussian mixture models applied to transaction
                  data to identify locations with similar demand
                  characteristics and ongoing work on a multi-armed
                  bandit approach to match incentives and ad
                  campaigns to locations and user groups within
                  them. To capture the impact of matches we model
                  user preferences as time-varying stochastic
                  processes that depend on the offered mechanism. We
                  are collaborating with the Seattle Department of
                  Transportation to test the proposed techniques in
                  a living lab scenario in which we target
                  information to potential parkers and gather
                  feedback via environmental sensors and user
                  surveys to assess outcomes.},
        URL = {http://cps-forces.org/pubs/281.html}
    }
    

Posted by Carolyn Winter on 24 Aug 2017.
Groups: forces
For additional information, see the Publications FAQ or contact webmaster at cps-forces org.

Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.