NY Statewide Behavioral Equity Impact Decision Support Tool with Replica

One of the enduring challenges in statewide transportation planning is that consistent population travel data remains scarce, particularly for underserved and rural communities with inequity issues. This is changing with the availability of large-scale ICT data. A one-year project was initiated to develop a behavioral equity impact decision support tool based on NY statewide synthetic population data provided by Replica Inc. First, a NY statewide model choice model is developed to deterministically fit heterogeneous coefficients for trips along each census block-group OD pair, called group-level agent-based mixed (GLAM) logit. Considerations were made for four population segments, six trip modes, and twelve attributes. Second, a decision support tool for statewide mobility service region design was proposed. The tool is based on an assortment optimization problem with agent-specific coefficients and linear constraints, which can be efficiently solved through linear or quadratic programming (depending on variant). The decision support tool is applied to optimize service regions with one of the three objectives: (1) maximizing the total revenue; (2) maximizing the total change of consumer surplus; (3) minimizing the disparity between disadvantaged and non-disadvantaged communities.

Presented by Xiyuan Ren; PHD Candidate, NYU; Joseph Chow, Associate Professor, NYU