The full text of this item is not available at this time because the student has placed this item under an embargo for a period of time. The Libraries are not authorized to provide a copy of this work during the embargo period, even for Texas A&M users with NetID.
Predicting Travel Behavior on Managed Lanes – A Behavioral Economics Approach
Abstract
On a freeway with managed lanes (MLs), travelers have an opportunity to choose between paying a toll and traveling on the generally faster MLs or traveling for free on the adjacent general-purpose lanes (GPLs). Traditional toll pricing models assume that all travelers are making a choice between these two lanes when they travel, mostly based on travel time savings versus toll tradeoff. However, recent research has shown that many travelers are not making that choice. In addition, many of these travelers who are making that choice appear to be making an irrational choice with respect to existing economic principles.
This research focused on predicting this behavior of travelers. The first step of this process was to classify them as choosers (people who choose between MLs and GPLs) and non-choosers (people who always use MLs or GPLs). Using data from a behavioral economics-based traffic experiment and a sophisticated travel survey, machine leaning techniques were used to develop models that could predict choosers and non-choosers and the variables those were best in that prediction. The experiment involved subjects repeatedly choosing between two roads for hundred rounds (periods). Subjects who took more time to complete a section of the survey and to verify their answers were more likely to be choosers. Direct responders during the traffic experiment were also more likely to be choosers. Certain socio-demographic factors, trip related factors and individual differences also had an impact in this prediction based on the study group analyzed. The impact of an informational nudge in choosing behavior was evaluated based on a treatment-control analysis. During the second half of the experiment, some subjects were given information about the travel time of the road they did not choose in the previous period. Direct responders and non-choosers were more likely to choose more with the nudge.
Subject
Managed LanesTravel Behavior
Behavioral Economics
Machine Learning
Congestion Pricing
Traffic Operations
TSMO
Citation
Ashraf, Sruthi (2022). Predicting Travel Behavior on Managed Lanes – A Behavioral Economics Approach. Doctoral dissertation, Texas A&M University. Available electronically from https : / /hdl .handle .net /1969 .1 /198696.