Return to search

The Mode Most Traveled: Parking Implications and Policy Responses

A disproportionate number of Americans drive to work alone – at the individual state level, the figure ranges from a low of 58% in New York to 85% in Alabama. What factors explain this travel behavior and what sort of policy responses are required to effect changes? In responding to this question, we used multiple test beds and made the case for a demand side management approach to remedy parking problems particularly observed in cities central business districts. To this end, we provide an overview of travel behavior and information on policy levers by generating detailed profiles that capture the travel behavior of commuters in the Pacific states of the continental United States. Building off the result that revealed San Francisco as an outlier, we examine the efficacy of modifying parking rates, via elasticity measures, to influence the demand for parking by developing a two-stage panel data regression optimization model for managing parking in the City of San Francisco. A key contribution of the research is deriving these price elasticities of parking demand estimates using panel data methods. Coefficient estimates from the panel data regression are used to fit a linear prediction model that is the primary input to the optimization model. The balance of the thesis focuses on parking information by discussing the design and implementation of ParkPGH, a novel smart parking application that provides real time and predictive information on garage parking availability in downtown Pittsburgh. At its core is a predictive model that uses as input historical parking, weather and event data to provide estimates of available parking spaces. We provide an example of the model implementation using data from the Theater Square garage where we utilize neural network-based predictors and multiple net searches to generate both continuous and binary estimates of parking availability. Provision was made for the binary classifier given the need to reduce the possibility of Type II errors.

Identiferoai:union.ndltd.org:cmu.edu/oai:repository.cmu.edu:dissertations-1766
Date01 December 2016
CreatorsFabusuyi, Olutayo G.
PublisherResearch Showcase @ CMU
Source SetsCarnegie Mellon University
Detected LanguageEnglish
Typetext
Formatapplication/pdf
SourceDissertations

Page generated in 0.0021 seconds