Network and station-level bike-sharing system prediction: a San Francisco bay area case study
Loading...
Collections
Author/Creator ORCID
Date
2021-07-08
Type of Work
Department
Program
Citation of Original Publication
Huthaifa I. Ashqar, Mohammed Elhenawy, Hesham A. Rakha, Mohammed Almannaa & Leanna House (2022) Network and station-level bike-sharing system prediction: a San Francisco bay area case study, Journal of Intelligent Transportation Systems, 26:5, 602-612, DOI: 10.1080/15472450.2021.1948412
Rights
This is the submitted manuscript of an article published by Taylor & Francis in Journal of Intelligent Transportation Systems on 08 Jul 2021, available online: http://www.tandfonline.com/https://doi.org/10.1080/15472450.2021.1948412
Subjects
Abstract
The paper develops models for modeling the availability of bikes in the San Francisco Bay Area
Bike Share System applying machine learning at two levels: network and station. Investigating
BSSs at the station-level is the full problem that would provide policymakers, planners, and
operators with the needed level of details to make important choices and conclusions. We used
Random Forest and Least-Squares Boosting as univariate regression algorithms to model the
number of available bikes at the station-level. For the multivariate regression, we applied Partial
Least-Squares Regression (PLSR) to reduce the needed prediction models and reproduce the
spatiotemporal interactions in different stations in the system at the network-level. Although
prediction errors were slightly lower in the case of univariate models, we found that the
multivariate model results were promising for the network-level prediction, especially in systems
where there is a relatively large number of stations that are spatially correlated. Moreover,
results of the station-level analysis suggested that demographic information and other
environmental variables were significant factors to model bikes in BSSs. We also demonstrated
that the available bikes modeled at the station-level at time 𝑡 had a notable influence on the bike
count models. Station neighbors and prediction horizon times were found to be significant
predictors, with 15 minutes being the most effective prediction horizon time.