Chow discusses microtransit deployment portfolio management using simulation-based data upscaling

Dr. Joseph Chow, Institute Associate Professor at NYU Tandon School of Engineering, presented “Microtransit Deployment Portfolio Management Using Simulation-Based Data Upscaling” for the UT-ITE seminar series on November 12, 2021.

Chow collaborated with PhD students Srushti Rath, Bingqing Liu and Gyuyeon Yoon on this project, with the support of the C2SMART Center and data-sharing from Via Transportation.

Chow opened the seminar with a brief definition of microtransit, explaining that microtransit is like the space in-between traditional public fixed-route transit and private ride-sharing services. It is a technology-enabled transit service that uses small vehicles to offer consumers fixed or dynamically-allocated routes on-demand.

To find market opportunities for microtransit deployment, Chow mimicked Via’s operation of pick-up and drop-off vans that make virtual stops based on real-time requests within a service region.

Chow observed that new services suggest a paradigm shift occurring in transportation planning: away from the traditional city/region-centric approach and towards operator-centric planning. Instead of transit services operated in single regions by public agencies, operator-centric planning includes multiple regions and involves collaboration between the public and private sectors.

Chow discussed the positive impact the deployment of microtransit can have on the economy, traffic congestion, and environment, and the potential insights that can be discovered from better forecasting modelling.

He presented the methodology to “upscale” the limited data available by using algorithms to fill in the gaps.

Chow explained the framework of the methodology. They used scenario generation and a market equilibrium model to generate input variables from the limited data in conjunction with public data of the targeted city for their forecast model. This allows them to forecast measures like Ridership Fleet VMT (Vehicle Miles Travelled).

Chow also refined the simulation to include individual travellers’ day-to-day adjustments (ride time, first/last mile access trips, and direct trips) and within-day microtransit adjustments (fleet sizes).

He then demonstrated how his model functioned. He discussed the parameters used and the demand models estimated for each city. The simulated model, using the limited data, “upscaled” the data to create portfolio forecast models that showed sufficient fit with only four city samples.

Chow concludes that under the emerging operator-centric planning paradigm, this tool can be used to help:

  • Microtransit services to identify and convince new cities to consider microtransit options
  • Government agencies to identify priority areas and develop a national portfolio dashboard

Watch the presentation video recording

Coming soon to the UT-ITE YouTube channel.


Due to transportation technologies having such heterogeneous impacts on different communities, there needs to be better tools to evaluate the deployment of emerging technologies with limited data. Microtransit is one such technology.

We propose a novel methodology to “upscale” the limited data available so that further decision-support analysis and forecast modelling can be achieved where none could prior. The methodology involves extending an initial day-to-day adjustment process to handle both first/last mile access trips and direct trips, updating a within-day microtransit simulator with a parametric design, and developing a scenario generation process.
The method is tested in a case study with data from Via for Salt Lake City, Austin, Cupertino, Sacramento, Columbus, and Jersey City showing an average 18% ridership error for the market equilibrium models. Data from four of those cities are upscaled to 326 scenarios to estimate forecast models for ridership and fleet vehicle-miles-traveled using Lasso regularization. The models have root mean squared error (RMSE) values between 37-45% of the averages, whereas using only four cities’ data would not produce any forecast model at all. The results show that variables with statistically significant positive impact on ridership and negative impact on vehicle-miles-traveled (VMT) include zones with more transit stops, higher employment, but lower “employment density × fixed fare.”

The models are then used to identify two alternative portfolios with similar fleet VMT as the original four cities but are forecast to have up to 1.9 times the ridership.

Watch the presentation video recording

Coming soon to the UT-ITE YouTube channel.

About the speaker

head shot of Joseph Chow
Professor Joseph Chow

Joseph Chow is an Institute Associate Professor at NYU Tandon School of Engineering’s Civil and Urban Engineering Department with affiliations at CUSP and Rudin Center for Transportation Policy & Management.

He is an NSF CAREER award recipient, a former Canada Research Chair, and the co-founding Deputy Director of the C2SMART transportation center at NYU. He is the Chair of the Subcommittee on Route Choice & Spatiotemporal Behavior at TRB. He has published about 70 journal articles since 2010 and is an editor for three transportation journals including Transportation Research Part B.

Dr. Chow received his PhD (’10) at UC Irvine and his MEng (’01) and BS (’00) at Cornell University.

Presented by University of Toronto ITE Student Chapter, UT-ITE.